- calculate() - Method in class org.neuroph.core.Layer
-
Performs calculaton for all neurons in this layer
- calculate() - Method in class org.neuroph.core.NeuralNetwork
-
Performs calculation on whole network
- calculate() - Method in class org.neuroph.core.Neuron
-
Calculates neuron's output
- calculate() - Method in class org.neuroph.nnet.comp.layer.CompetitiveLayer
-
Performs calculaton for all neurons in this layer
- calculate() - Method in class org.neuroph.nnet.comp.neuron.BiasNeuron
-
- calculate() - Method in class org.neuroph.nnet.comp.neuron.CompetitiveNeuron
-
- calculate() - Method in class org.neuroph.nnet.comp.neuron.DelayedNeuron
-
- calculate() - Method in class org.neuroph.nnet.comp.neuron.InputNeuron
-
Calculate method of this type of neuron does nothing
- calculate() - Method in class org.neuroph.nnet.comp.neuron.InputOutputNeuron
-
Calculates neuron output
- calculate() - Method in class org.neuroph.nnet.comp.neuron.ThresholdNeuron
-
Calculates neuron's output
- calculateErrorAndUpdateHiddenNeurons() - Method in class org.neuroph.nnet.learning.BackPropagation
-
This method implements weights adjustment for the hidden layers
- calculateErrorAndUpdateHiddenNeurons() - Method in class org.neuroph.nnet.learning.ConvolutionalBackpropagation
-
- calculateErrorAndUpdateHiddenNeurons() - Method in class org.neuroph.nnet.learning.MomentumBackpropagation
-
This method implements weights adjustment for the hidden layers
Uses parallel processing on each layer with 100 or more neurons and a regular loop if less.
- calculateErrorAndUpdateOutputNeurons(double[]) - Method in class org.neuroph.nnet.learning.BackPropagation
-
This method implements weights update procedure for the output neurons
Calculates delta/error and calls updateNeuronWeights to update neuron's weights
for each output neuron
- calculateHiddenNeuronError(Neuron) - Method in class org.neuroph.nnet.learning.BackPropagation
-
Calculates and returns the neuron's error (neuron's delta) for the given neuron param
- calculateHiddenNeuronError(Neuron) - Method in class org.neuroph.nnet.learning.ConvolutionalBackpropagation
-
- calculateStatistics() - Method in class org.neuroph.util.benchmark.BenchmarkTaskResults
-
- calculateStatistics() - Method in class org.neuroph.util.DataSetStatistics
-
Calculates basic statistics by columns of the dataset.
- calculateWeightChanges(double[]) - Method in class org.neuroph.core.learning.SupervisedLearning
-
This method should implement the weights update procedure for the whole network
for the given output error vector.
- calculateWeightChanges(double[]) - Method in class org.neuroph.nnet.learning.BackPropagation
-
This method implements weight update procedure for the whole network
for the specified output error vector.
- calculateWeightChanges(double[]) - Method in class org.neuroph.nnet.learning.BinaryDeltaRule
-
This method implements weight update procedure for the whole network for
this learning rule
- calculateWeightChanges(double[]) - Method in class org.neuroph.nnet.learning.LMS
-
This method calculates weight change for the network's output neurons for the given output error vector.
- calculateWeightChanges(Neuron) - Method in class org.neuroph.nnet.learning.LMS
-
This method calculates weights changes for the single neuron.
- calculateWeightChanges(Neuron) - Method in class org.neuroph.nnet.learning.ManhattanPropagation
-
- calculateWeightChanges(Neuron) - Method in class org.neuroph.nnet.learning.MomentumBackpropagation
-
This method implements weights update procedure for the single neuron for
the back propagation with momentum factor
- calculateWeightChanges(Neuron) - Method in class org.neuroph.nnet.learning.PerceptronLearning
-
This method implements weights update procedure for the single neuron
In addition to weights change in LMS it applies change to neuron's threshold
- calculateWeightChanges(Neuron) - Method in class org.neuroph.nnet.learning.QuickPropagation
-
- calculateWeightChanges(Neuron) - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
Calculate and sum gradients for each neuron's weight, the actual weight update is done in batch mode.
- calculateWeightChanges(double[]) - Method in class org.neuroph.nnet.learning.SigmoidDeltaRule
-
This method implements weight update procedure for the whole network for
this learning rule
- calculateWeightChanges(double[]) - Method in class org.neuroph.nnet.learning.SimulatedAnnealingLearning
-
Not used.
- calculateWeightChanges(double[]) - Method in class org.neuroph.nnet.learning.SupervisedHebbianLearning
-
This method implements weight update procedure for the whole network for
this learning rule
- CLASS_LABELS - Static variable in class org.neuroph.eval.ClassifierEvaluator.Binary
-
- ClassificationMetrics - Class in org.neuroph.eval.classification
-
Container class for all metrics which use confusion matrix for their computation
Based on:
http://java-ml.sourceforge.net/api/0.1.7/net/sf/javaml/classification/evaluation/PerformanceMeasure.html
http://sourceforge.net/p/java-ml/java-ml-code/ci/a25ddde7c3677da44e47a643f88e32e2c8bbc32f/tree/net/sf/javaml/classification/evaluation/PerformanceMeasure.java
http://en.wikipedia.org/wiki/Matthews_correlation_coefficient
- ClassificationMetrics(int, int, int, int) - Constructor for class org.neuroph.eval.classification.ClassificationMetrics
-
Constructs a new measure using arguments
TODO: add class to which measure corresponds?
- ClassificationMetrics.Stats - Class in org.neuroph.eval.classification
-
- ClassificationResult - Class in org.neuroph.eval.classification
-
Ovu klasu definitivno izabciti
KOristi se samo getMaxOutput koja uz to i potpuno nebulozna jer vraca ClassificationResult
vidi samo zasta nam treba u McNemar
a pri tom uvek se poziva getActual
Wrapper class used for ordering classification results
- ClassificationResult(int, double) - Constructor for class org.neuroph.eval.classification.ClassificationResult
-
- Classifier - Class in org.neuroph.eval.classification
-
Classifier plugin for neurla networks
- Classifier() - Constructor for class org.neuroph.eval.classification.Classifier
-
- ClassifierEvaluator - Class in org.neuroph.eval
-
- ClassifierEvaluator.Binary - Class in org.neuroph.eval
-
Binary evaluator used for computation of metrics in case when data has only one output result (one output neuron)
- ClassifierEvaluator.MultiClass - Class in org.neuroph.eval
-
Evaluator used for computation of metrics in case when data has
multiple classes - one vs many classification
- classify(double[]) - Method in class org.neuroph.eval.classification.Classifier
-
- clear() - Method in class org.neuroph.core.data.DataSet
-
Removes all alements from training set
- clone() - Method in class org.neuroph.core.Connection
-
- clone() - Method in class org.neuroph.core.Neuron
-
- clone() - Method in class org.neuroph.core.Weight
-
Returns cloned instance of this weight
Important: trainingData will be lost in cloned instance
- close() - Method in interface org.neuroph.util.io.InputAdapter
-
Close data source after reading is finnished.
- close() - Method in class org.neuroph.util.io.InputStreamAdapter
-
- close() - Method in class org.neuroph.util.io.JDBCInputAdapter
-
Closes result set used as data source.
- close() - Method in class org.neuroph.util.io.JDBCOutputAdapter
-
- close() - Method in interface org.neuroph.util.io.OutputAdapter
-
Close destination after writing is finnished.
- close() - Method in class org.neuroph.util.io.OutputStreamAdapter
-
Closes output stream.
- Cluster - Class in org.neuroph.nnet.learning.kmeans
-
This class represents a single cluster, with corresponding centroid and assigned vectors
- Cluster() - Constructor for class org.neuroph.nnet.learning.kmeans.Cluster
-
- CompetitiveLayer - Class in org.neuroph.nnet.comp.layer
-
Represents layer of competitive neurons, and provides methods for competition.
- CompetitiveLayer(int, NeuronProperties) - Constructor for class org.neuroph.nnet.comp.layer.CompetitiveLayer
-
Create an instance of CompetitiveLayer with the specified number of
neurons with neuron properties
- CompetitiveLearning - Class in org.neuroph.nnet.learning
-
Competitive learning rule.
- CompetitiveLearning() - Constructor for class org.neuroph.nnet.learning.CompetitiveLearning
-
Creates new instance of CompetitiveLearning
- CompetitiveNetwork - Class in org.neuroph.nnet
-
Two layer neural network with competitive learning rule.
- CompetitiveNetwork(int, int) - Constructor for class org.neuroph.nnet.CompetitiveNetwork
-
Creates new competitive network with specified neuron number
- CompetitiveNeuron - Class in org.neuroph.nnet.comp.neuron
-
Provides neuron behaviour specific for competitive neurons which are used in
competitive layers, and networks with competitive learning.
- CompetitiveNeuron(InputFunction, TransferFunction) - Constructor for class org.neuroph.nnet.comp.neuron.CompetitiveNeuron
-
Creates an instance of CompetitiveNeuron with specified input and transfer functions
- ConfusionMatrix - Class in org.neuroph.eval.classification
-
Confusion matrix container, holds class labels and matrix values .
- ConfusionMatrix(String[]) - Constructor for class org.neuroph.eval.classification.ConfusionMatrix
-
Creates new confusion matrix with specified class labels and number of classes
- connectFeatureMaps(FeatureMapsLayer, FeatureMapsLayer, int, int) - Static method in class org.neuroph.nnet.comp.ConvolutionalUtils
-
Creates connections between two feature maps - not used???
- connectInputsToOutputs() - Method in class org.neuroph.nnet.MultiLayerPerceptron
-
- Connection - Class in org.neuroph.core
-
Weighted connection to another neuron.
- Connection(Neuron, Neuron) - Constructor for class org.neuroph.core.Connection
-
Creates a new connection between specified neurons with random weight
- Connection(Neuron, Neuron, Weight) - Constructor for class org.neuroph.core.Connection
-
Creates a new connection to specified neuron with specified weight object
- Connection(Neuron, Neuron, double) - Constructor for class org.neuroph.core.Connection
-
Creates a new connection to specified neuron with specified weight value
- ConnectionFactory - Class in org.neuroph.util
-
Provides methods to connect neurons by creating Connection objects.
- ConnectionFactory() - Constructor for class org.neuroph.util.ConnectionFactory
-
- connectMaps(FeatureMapLayer, FeatureMapLayer) - Method in class org.neuroph.nnet.comp.layer.ConvolutionalLayer
-
Creates connections with shared weights between two feature maps Assumes
that toMap is from Convolutional layer.
- connectMaps(FeatureMapLayer, FeatureMapLayer) - Method in class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
Creates connections between two feature maps.
- connectMaps(FeatureMapLayer, FeatureMapLayer) - Method in class org.neuroph.nnet.comp.layer.InputMapsLayer
-
- connectMaps(FeatureMapLayer, FeatureMapLayer) - Method in class org.neuroph.nnet.comp.layer.PoolingLayer
-
Creates connections with shared weights between two feature maps
Assumes that toMap is from Pooling layer.
- convertToVector(double[]) - Static method in class org.neuroph.util.VectorParser
-
- ConvolutionalBackpropagation - Class in org.neuroph.nnet.learning
-
- ConvolutionalBackpropagation() - Constructor for class org.neuroph.nnet.learning.ConvolutionalBackpropagation
-
- ConvolutionalLayer - Class in org.neuroph.nnet.comp.layer
-
Convolutional layer is a special type of layer, used in convolutional neural
networks.
- ConvolutionalLayer(FeatureMapsLayer, Dimension2D, int) - Constructor for class org.neuroph.nnet.comp.layer.ConvolutionalLayer
-
Creates convolutional layer with specified kernel, appropriate map
dimensions in regard to previous layer (fromLayer param) and specified
number of feature maps with default neuron settings for convolutional
layer.
- ConvolutionalLayer(FeatureMapsLayer, Dimension2D, int, Class<? extends TransferFunction>) - Constructor for class org.neuroph.nnet.comp.layer.ConvolutionalLayer
-
Creates convolutional layer with specified kernel, appropriate map
dimensions in regard to previous layer (fromLayer param) and specified
number of feature maps with default neuron settings for convolutional
layer.
- ConvolutionalLayer(FeatureMapsLayer, Dimension2D, int, NeuronProperties) - Constructor for class org.neuroph.nnet.comp.layer.ConvolutionalLayer
-
Creates convolutional layer with specified kernel, appropriate map
dimensions in regard to previous layer (fromLayer param) and specified
number of feature maps with given neuron properties.
- ConvolutionalNetwork - Class in org.neuroph.nnet
-
Convolutional neural network with backpropagation algorithm modified for
convolutional networks.
- ConvolutionalNetwork() - Constructor for class org.neuroph.nnet.ConvolutionalNetwork
-
- ConvolutionalNetwork.Builder - Class in org.neuroph.nnet
-
- ConvolutionalUtils - Class in org.neuroph.nnet.comp
-
Utility functions for convolutional networks
- ConvolutionalUtils() - Constructor for class org.neuroph.nnet.comp.ConvolutionalUtils
-
- correlationCoefficient - Variable in class org.neuroph.eval.classification.ClassificationMetrics.Stats
-
- createAdaline(int) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Adaline network
- createBam(int, int) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of BAM network
- createCompetitiveNetwork(int, int) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of competitive network
- createConnection(Neuron, Neuron, double) - Method in class org.neuroph.core.NeuralNetwork
-
Creates connection with specified weight value between specified neurons
- createConnection(Neuron, Neuron) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates connection between two specified neurons
- createConnection(Neuron, Neuron, double) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates connection between two specified neurons
- createConnection(Neuron, Neuron, double, int) - Static method in class org.neuroph.util.ConnectionFactory
-
- createConnection(Neuron, Neuron, Weight) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates connection between two specified neurons
- createConnection(Neuron, Layer) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates connectivity between specified neuron and all neurons in specified layer
- createFeatureMaps(int, Dimension2D, Dimension2D, NeuronProperties) - Method in class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
Creates and adds specified number of feature maps to this layer
- createFromFile(String, int, int, String, boolean) - Static method in class org.neuroph.core.data.DataSet
-
Creates and returns data set from specified csv file
- createFromFile(String, int, int, String) - Static method in class org.neuroph.core.data.DataSet
-
Creates and returns data set from specified csv file
- createFromFile(File) - Static method in class org.neuroph.core.NeuralNetwork
-
Loads and return s neural network instance from specified file
- createFromFile(String) - Static method in class org.neuroph.core.NeuralNetwork
-
- createFromMatrix(ConfusionMatrix) - Static method in class org.neuroph.eval.classification.ClassificationMetrics
-
- createHopfield(int) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Hopfield network
- createInstar(int) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Instar network
- createKeys(String...) - Method in class org.neuroph.util.Properties
-
- createKohonen(int, int) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Kohonen network
- createLayer(int, NeuronProperties) - Static method in class org.neuroph.util.LayerFactory
-
Creates and returns instance of Layer with specified number of neurons with specified properties
- createLayer(int, TransferFunctionType) - Static method in class org.neuroph.util.LayerFactory
-
- createLayer(int, Class<? extends TransferFunction>) - Static method in class org.neuroph.util.LayerFactory
-
- createLayer(List<NeuronProperties>) - Static method in class org.neuroph.util.LayerFactory
-
- createMaxNet(int) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Max Net network
- createMLPerceptron(String, TransferFunctionType) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Multi Layer Perceptron
- createMLPerceptron(String, TransferFunctionType, Class, boolean, boolean) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Multi Layer Perceptron
- createNeuron(NeuronProperties) - Static method in class org.neuroph.util.NeuronFactory
-
Creates and returns neuron instance according to the given specification in neuronProperties.
- createOutstar(int) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Outstar network
- createPerceptron(int, int, TransferFunctionType) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Perceptron network
- createPerceptron(int, int, TransferFunctionType, Class) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Perceptron network
- createRbfNetwork(int, int, int) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of RBF network
- createSupervisedHebbian(int, int, TransferFunctionType) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Hebbian network
- createTrainingAndTestSubsets(double, double) - Method in class org.neuroph.core.data.DataSet
-
Returns training and test subsets in the specified percent ratio
- createUnsupervisedHebbian(int, int, TransferFunctionType) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Creates and returns a new instance of Unsupervised Hebbian Network
- CrossValidationBak - Class in org.neuroph.eval
-
This class implements multithreaded cross validation procedure.
- CrossValidationBak(NeuralNetwork, DataSet, int) - Constructor for class org.neuroph.eval.CrossValidationBak
-
Creates a new instance of crrossvalidation for specified neural network, data set and number of folds.
- currentIteration - Variable in class org.neuroph.core.learning.IterativeLearning
-
Current iteration counter
- DataSet - Class in org.neuroph.core.data
-
This class represents a collection of data rows (DataSetRow instances) used
for training and testing neural network.
- DataSet(int) - Constructor for class org.neuroph.core.data.DataSet
-
Creates an instance of new empty training set
- DataSet(int, int) - Constructor for class org.neuroph.core.data.DataSet
-
Creates an instance of new empty training set
- DataSetColumnType - Enum in org.neuroph.util
-
- DataSetRow - Class in org.neuroph.core.data
-
This class represents single data row in a data set.
- DataSetRow(String, String) - Constructor for class org.neuroph.core.data.DataSetRow
-
Creates new training element with specified input and desired output
vectors specifed as strings
- DataSetRow(double[], double[]) - Constructor for class org.neuroph.core.data.DataSetRow
-
Creates new training element with specified input and desired output
vectors
- DataSetRow(double...) - Constructor for class org.neuroph.core.data.DataSetRow
-
Creates new training element with input array
- DataSetRow(ArrayList<Double>, ArrayList<Double>) - Constructor for class org.neuroph.core.data.DataSetRow
-
Creates new training element with specified input and desired output
vectors
- DataSetRow(ArrayList<Double>) - Constructor for class org.neuroph.core.data.DataSetRow
-
- DataSets - Class in org.neuroph.core.data
-
- DataSets() - Constructor for class org.neuroph.core.data.DataSets
-
- DataSetStatistics - Class in org.neuroph.util
-
This class calculates statistics for data set.
- DataSetStatistics(DataSet) - Constructor for class org.neuroph.util.DataSetStatistics
-
- DataSetStats - Class in org.neuroph.util
-
Utility class with methods for calculating dataset statistics
Calculate everything in one pass and expose as attributes - like summary() in R
Not only for inputs but also for outputs
- DataSetStats() - Constructor for class org.neuroph.util.DataSetStats
-
- dec(double) - Method in class org.neuroph.core.Weight
-
Decreases the weight for specified amount
- DecimalScaleNormalizer - Class in org.neuroph.util.data.norm
-
Decimal scaling normalization method, which normalize data by moving decimal
point in regard to max element in training set (by columns) Normalization is
done according to formula: normalizedVector[i] = vector[i] / scaleFactor[i]
- DecimalScaleNormalizer(DataSet) - Constructor for class org.neuroph.util.data.norm.DecimalScaleNormalizer
-
Initializes normalizer, finds right scale factor for each input and output column in vectors.
- DEFAULT_FULL_CONNECTED_NEURON_PROPERTIES - Static variable in class org.neuroph.nnet.ConvolutionalNetwork.Builder
-
- DEFAULT_NEURON_PROP - Static variable in class org.neuroph.nnet.comp.layer.ConvolutionalLayer
-
Default neuron properties for convolutional layer
- DEFAULT_NEURON_PROP - Static variable in class org.neuroph.nnet.comp.layer.InputMapsLayer
-
Default neuron properties for InputMapsLayer is InputNeuron with Linear transfer function
- DEFAULT_NEURON_PROP - Static variable in class org.neuroph.nnet.comp.layer.PoolingLayer
-
Default neuron properties for pooling layer
- DelayedConnection - Class in org.neuroph.nnet.comp
-
Represents the connection between neurons which can delay signal.
- DelayedConnection(Neuron, Neuron, double, int) - Constructor for class org.neuroph.nnet.comp.DelayedConnection
-
Creates an instance of delayed connection to cpecified neuron and
with specified weight
- DelayedNeuron - Class in org.neuroph.nnet.comp.neuron
-
Provides behaviour for neurons with delayed output.
- DelayedNeuron(InputFunction, TransferFunction) - Constructor for class org.neuroph.nnet.comp.neuron.DelayedNeuron
-
Creates an instance of neuron which can delay output
- delta - Variable in class org.neuroph.core.Neuron
-
Local error (delta) for this neuron *
- determineArraySize(NeuralNetwork) - Static method in class org.neuroph.util.NeuralNetworkCODEC
-
Determine the array size for the given neural network.
- Difference - Class in org.neuroph.core.input
-
Performs the vector difference operation on input and
weight vector.
- Difference() - Constructor for class org.neuroph.core.input.Difference
-
- Dimension2D - Class in org.neuroph.nnet.comp
-
Dimensions (width and height) of the Layer2D
- Dimension2D(int, int) - Constructor for class org.neuroph.nnet.comp.Dimension2D
-
Creates new dimensions with specified width and height
- distanceFrom(KVector) - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
Calculates and returns euclidean distance of this vector from the given cluster
- DistortRandomizer - Class in org.neuroph.util.random
-
This class provides distort randomization technique, which distorts existing
weight values using specified distortion factor.
- DistortRandomizer(double) - Constructor for class org.neuroph.util.random.DistortRandomizer
-
Create a new instance of DistortRandomizer with specified distortion factor
- doBatchWeightsUpdate() - Method in class org.neuroph.core.learning.SupervisedLearning
-
This method updates network weights in batch mode - use accumulated weights change stored in Weight.deltaWeight
It is executed after each learning epoch, only if learning is done in batch mode.
- doBatchWeightsUpdate() - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- doClustering() - Method in class org.neuroph.nnet.learning.kmeans.KMeansClustering
-
- doLearningEpoch(DataSet) - Method in class org.neuroph.core.learning.IterativeLearning
-
Override this method to implement specific learning epoch - one learning
iteration, one pass through whole training set
- doLearningEpoch(DataSet) - Method in class org.neuroph.core.learning.SupervisedLearning
-
This method implements basic logic for one learning epoch for the
supervised learning algorithms.
- doLearningEpoch(DataSet) - Method in class org.neuroph.core.learning.UnsupervisedLearning
-
This method does one learning epoch for the unsupervised learning rules.
- doLearningEpoch(DataSet) - Method in class org.neuroph.nnet.learning.CompetitiveLearning
-
This method does one learning epoch for the unsupervised learning rules.
- doLearningEpoch(DataSet) - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- doLearningEpoch(DataSet) - Method in class org.neuroph.nnet.learning.SimulatedAnnealingLearning
-
Perform one simulated annealing epoch.
- doLearningEpoch(DataSet, double) - Method in class org.neuroph.nnet.learning.SimulatedAnnealingLearning
-
- doLearningEpoch(DataSet) - Method in class org.neuroph.nnet.learning.UnsupervisedHebbianLearning
-
This method does one learning epoch for the unsupervised learning rules.
- doOneLearningIteration(DataSet) - Method in class org.neuroph.core.learning.IterativeLearning
-
Runs one learning iteration with the specified training set and fires
event to notify observers.
- DynamicBackPropagation - Class in org.neuroph.nnet.learning
-
Backpropagation learning rule with dynamic learning rate and momentum
- DynamicBackPropagation() - Constructor for class org.neuroph.nnet.learning.DynamicBackPropagation
-
- FeatureMapLayer - Class in org.neuroph.nnet.comp.layer
-
FeatureMapLayer Layer provides 2D layout of the neurons in layer.
- FeatureMapLayer(Dimension2D, NeuronProperties) - Constructor for class org.neuroph.nnet.comp.layer.FeatureMapLayer
-
Creates an empty 2D layer with specified dimensions
- FeatureMapLayer(Dimension2D, Dimension2D) - Constructor for class org.neuroph.nnet.comp.layer.FeatureMapLayer
-
Creates an empty 2D layer with specified dimensions and kernel
- FeatureMapLayer(Dimension2D, NeuronProperties, Dimension2D) - Constructor for class org.neuroph.nnet.comp.layer.FeatureMapLayer
-
Creates 2D layer with specified dimensions, filled with neurons with
specified properties
- FeatureMapsLayer - Class in org.neuroph.nnet.comp.layer
-
This class represents an array of feature maps which are 2 dimensional layers
(Layer2D instances) and it is base class for Convolution and Pooling layers,
which are used in ConvolutionalNetwork
- FeatureMapsLayer() - Constructor for class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
Creates a new empty feature maps layer with specified kernel
- FeatureMapsLayer(Dimension2D) - Constructor for class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
Creates a new empty feature maps layer with specified kernel and
feature map dimensions.
- FeatureMapsLayer(Dimension2D, Dimension2D, int, NeuronProperties) - Constructor for class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
Creates new feature maps layer with specified kernel and feature maps.
- FeatureMapsLayer(Dimension2D, int, NeuronProperties) - Constructor for class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
- FileInputAdapter - Class in org.neuroph.util.io
-
Implementation of InputAdapter interface for reading neural network inputs from files.
- FileInputAdapter(File) - Constructor for class org.neuroph.util.io.FileInputAdapter
-
Creates a new FileInputAdapter by opening a connection to an actual file,
specified by the file param
- FileInputAdapter(String) - Constructor for class org.neuroph.util.io.FileInputAdapter
-
Creates a new FileInputAdapter by opening a connection to an actual file,
specified by the fileName param
- FileOutputAdapter - Class in org.neuroph.util.io
-
Implementation of OutputAdapter interface for writing neural network outputs to files.
- FileOutputAdapter(File) - Constructor for class org.neuroph.util.io.FileOutputAdapter
-
Creates a new FileOutputAdapter by opening a connection to an actual file,
specified by the file param
- FileOutputAdapter(String) - Constructor for class org.neuroph.util.io.FileOutputAdapter
-
Creates a new FileOutputAdapter by opening a connection to an actual file,
specified by the fileName param
- fireLearningEvent(LearningEvent) - Method in class org.neuroph.core.learning.LearningRule
-
- fireNetworkEvent(NeuralNetworkEvent) - Method in class org.neuroph.core.NeuralNetwork
-
- FoldResult - Class in org.neuroph.eval
-
Result from single cross-validation fold, includes neural network, training and validation set,
and fold evaluation results (at the moment only confsionMatrix)
TODO: add different eveluation metrics, for regression too.
- FoldResult(NeuralNetwork, DataSet, DataSet) - Constructor for class org.neuroph.eval.FoldResult
-
- forwardConnect(Layer, Layer, double) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates forward connectivity pattern between the specified layers
- forwardConnect(Layer, Layer) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates forward connection pattern between specified layers
- FREQ - Static variable in class org.neuroph.util.DataSetStatistics
-
- fromNeuron - Variable in class org.neuroph.core.Connection
-
From neuron for this connection (source neuron).
- fScore - Variable in class org.neuroph.eval.classification.ClassificationMetrics.Stats
-
- fullConnect(Layer, Layer) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates full connectivity between the two specified layers
- fullConnect(Layer, Layer, boolean) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates full connectivity between the two specified layers
- fullConnect(Layer, Layer, double) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates full connectivity between two specified layers with specified
weight for all connections
- fullConnect(Layer) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates full connectivity within layer - each neuron with all other
within the same layer
- fullConnect(Layer, double) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates full connectivity within layer - each neuron with all other
within the same layer with the specified weight values for all
conections.
- fullConnect(Layer, double, int) - Static method in class org.neuroph.util.ConnectionFactory
-
Creates full connectivity within layer - each neuron with all other
within the same layer with the specified weight and delay values for all
conections.
- fullConnectMapLayers(FeatureMapsLayer, FeatureMapsLayer) - Static method in class org.neuroph.nnet.comp.ConvolutionalUtils
-
Creates full connectivity between feature maps in two layers
- Gaussian - Class in org.neuroph.core.transfer
-
Gaussian neuron transfer function.
- Gaussian() - Constructor for class org.neuroph.core.transfer.Gaussian
-
Creates an instance of Gaussian neuron transfer
- Gaussian(Properties) - Constructor for class org.neuroph.core.transfer.Gaussian
-
Creates an instance of Gaussian neuron transfer function with the
specified properties.
- GaussianRandomizer - Class in org.neuroph.util.random
-
This class provides Gaussian randomization technique using Box Muller method.
- GaussianRandomizer(double, double) - Constructor for class org.neuroph.util.random.GaussianRandomizer
-
- GeneralizedHebbianLearning - Class in org.neuroph.nnet.learning
-
A variant of Hebbian learning called Generalized Hebbian learning.
- GeneralizedHebbianLearning() - Constructor for class org.neuroph.nnet.learning.GeneralizedHebbianLearning
-
- get(int) - Method in class org.neuroph.core.data.DataSet
-
- get(int, int) - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
- getAccuracy() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
Calculate and return classification accuracy measure.
- getAmplitude() - Method in class org.neuroph.core.transfer.Tanh
-
Returns the amplitude parameter of this function
- getArea() - Method in class org.neuroph.nnet.comp.Kernel
-
Returns area of this kernel (width*height)
- getAverageTestTime() - Method in class org.neuroph.util.benchmark.BenchmarkTaskResults
-
- getAvgSum() - Method in class org.neuroph.nnet.learning.kmeans.Cluster
-
Calculate and return avg sum vector for all vectors
- getBalancedClassificationRate() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
- getBias() - Method in class org.neuroph.nnet.comp.neuron.InputOutputNeuron
-
Returns bias value for this neuron
- getCentroid() - Method in class org.neuroph.nnet.learning.kmeans.Cluster
-
- getClassIdx() - Method in class org.neuroph.eval.classification.ClassificationResult
-
- getClassificationMetricses() - Method in class org.neuroph.eval.EvaluationResult
-
- getClassLabel() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
Returns class label for
- getClassLabels() - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
- getCluster() - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
- getClusters() - Method in class org.neuroph.nnet.learning.kmeans.KMeansClustering
-
- getColumnName(int) - Method in class org.neuroph.core.data.DataSet
-
- getColumnNames() - Method in class org.neuroph.core.data.DataSet
-
- getColumnType(int) - Method in class org.neuroph.core.data.DataSet
-
- getColumnTypes() - Method in class org.neuroph.core.data.DataSet
-
- getConfusionMatrix() - Method in class org.neuroph.eval.EvaluationResult
-
- getConfusionMatrix() - Method in class org.neuroph.eval.FoldResult
-
- getConnectionFrom(Neuron) - Method in class org.neuroph.core.Neuron
-
Gets input connection from the specified neuron * @param fromNeuron
neuron connected to this neuron as input
- getConnectionsFromOtherLayers() - Method in class org.neuroph.nnet.comp.neuron.CompetitiveNeuron
-
Returns collection of connections from other layers
- getCurrentIteration() - Method in class org.neuroph.core.learning.IterativeLearning
-
Returns current iteration of this learning algorithm
- getDataSet() - Method in class org.neuroph.eval.EvaluationResult
-
- getDataSet() - Method in class org.neuroph.nnet.learning.kmeans.KMeansClustering
-
- getDataSet() - Method in class org.neuroph.nnet.learning.knn.KNearestNeighbour
-
- getDataSet() - Method in class org.neuroph.util.DataSetStatistics
-
Get original data set.
- getDecreaseFactor() - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- getDelay() - Method in class org.neuroph.nnet.comp.DelayedConnection
-
Returns delay value for this connection
- getDelta() - Method in class org.neuroph.core.Neuron
-
Returns delta (error) for this neuron.
- getDerivative(double) - Method in class org.neuroph.core.transfer.Gaussian
-
- getDerivative(double) - Method in class org.neuroph.core.transfer.Linear
-
- getDerivative(double) - Method in class org.neuroph.core.transfer.Log
-
- getDerivative(double) - Method in class org.neuroph.core.transfer.RectifiedLinear
-
- getDerivative(double) - Method in class org.neuroph.core.transfer.Sigmoid
-
- getDerivative(double) - Method in class org.neuroph.core.transfer.Sin
-
- getDerivative(double) - Method in class org.neuroph.core.transfer.Tanh
-
Returns the derivative of this function evaluated at x=input
- getDerivative(double) - Method in class org.neuroph.core.transfer.TransferFunction
-
Returns the first derivative of this function.
- getDesiredOutput() - Method in class org.neuroph.core.data.DataSetRow
-
- getDimensions() - Method in class org.neuroph.nnet.comp.layer.FeatureMapLayer
-
Returns dimensions of this layer
- getDistance() - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
- getElapsedTime() - Method in class org.neuroph.util.benchmark.Stopwatch
-
Returns elapsed time in milliseconds between calls to start and stop methods
If the watch has never been started, returns zero
- getElapsedTimes() - Method in class org.neuroph.util.benchmark.BenchmarkTaskResults
-
- getErrorCorrection() - Method in class org.neuroph.nnet.learning.BinaryDeltaRule
-
Gets the errorCorrection parametar
- getErrorFunction() - Method in class org.neuroph.core.learning.SupervisedLearning
-
- getErrorRate() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
A number of wrong predictions made divided by the total number of predictions made.
- getEvaluation() - Method in class org.neuroph.eval.CrossValidationBak
-
- getEvaluator(Class<T>) - Method in class org.neuroph.eval.CrossValidationBak
-
- getEvaluator(Class<T>) - Method in class org.neuroph.eval.Evaluation
-
- getEvaluators() - Method in class org.neuroph.eval.Evaluation
-
Return all evaluators used for evaluation
- getEventType() - Method in class org.neuroph.core.events.LearningEvent
-
- getEventType() - Method in class org.neuroph.core.events.NeuralNetworkEvent
-
- getFalseDiscoveryRate() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
- getFalseNegative(int) - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
- getFalseNegativeRate() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
- getFalsePositive(int) - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
- getFalsePositiveRate() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
- getFeatureMap(int) - Method in class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
Returns feature map (Layer2D) at specified index
- getFeatureMaps() - Method in class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
- getFilePath() - Method in class org.neuroph.core.data.DataSet
-
Returns full file path for this training set
- getFMeasure() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
Calculates F-score for beta equal to 1.
- getFMeasure(int) - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
Returns the F-score.
- getFrequency() - Method in class org.neuroph.util.DataSetStatistics
-
Get data set frequency for nominal columns.
- getFromNeuron() - Method in class org.neuroph.core.Connection
-
Gets from neuron for this connection
- getHeight() - Method in class org.neuroph.nnet.comp.Dimension2D
-
- getHeight() - Method in class org.neuroph.nnet.comp.Kernel
-
Returns height of this kernel
- getHeight() - Method in class org.neuroph.nnet.comp.layer.FeatureMapLayer
-
Returns height of this layer
- getHighLimit() - Method in class org.neuroph.util.data.norm.RangeNormalizer
-
- getIncreaseFactor() - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- getInitialDelta() - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- getInput() - Method in class org.neuroph.core.Connection
-
Returns input received through this connection - the activation that
comes from the output of the cell on the other end of connection
Todo: make this final and solve delayed neuron connection in a different way
- getInput() - Method in class org.neuroph.core.data.DataSetRow
-
Returns input vector
- getInput() - Method in class org.neuroph.nnet.comp.DelayedConnection
-
Gets delayed input through this connection
- getInputConnections() - Method in class org.neuroph.core.Neuron
-
Returns input connections for this neuron
- getInputFunction() - Method in class org.neuroph.core.Neuron
-
Returns input function
- getInputFunction() - Method in class org.neuroph.util.NeuronProperties
-
- getInputFunctions() - Method in class org.neuroph.util.Neuroph
-
- getInputNeurons() - Method in class org.neuroph.core.NeuralNetwork
-
Returns input neurons
- getInputsCount() - Method in class org.neuroph.core.NeuralNetwork
-
Gets number of input neurons
- getInputSize() - Method in class org.neuroph.core.data.DataSet
-
Returns input vector size of training elements in this training set This
method is implementation of EngineIndexableSet interface, and it is added
to provide compatibility with Encog data sets and FlatNetwork
- getInstance() - Static method in class org.neuroph.util.Neuroph
-
- getIntensity() - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
Calculates and returns intensity of this vector
- getItems() - Method in class org.neuroph.core.data.DataSet
-
- getIteration() - Method in class org.neuroph.nnet.learning.KohonenLearning
-
- getKernel() - Method in class org.neuroph.nnet.comp.layer.FeatureMapLayer
-
- getKNearestNeighbours(KVector, int) - Method in class org.neuroph.nnet.learning.knn.KNearestNeighbour
-
http://en.wikipedia.org/wiki/Selection_algorithm
- getLabel() - Method in class org.neuroph.core.data.DataSet
-
Returns label for this training set
- getLabel() - Method in class org.neuroph.core.data.DataSetRow
-
Get training element label
- getLabel() - Method in class org.neuroph.core.Layer
-
Get layer label
- getLabel() - Method in class org.neuroph.core.NeuralNetwork
-
Get network label
- getLabel() - Method in class org.neuroph.core.Neuron
-
Returns label for this neuron
- getLabel() - Method in class org.neuroph.eval.classification.ClassificationResult
-
- getLayerAt(int) - Method in class org.neuroph.core.NeuralNetwork
-
Returns layer at specified index
- getLayers() - Method in class org.neuroph.core.NeuralNetwork
-
Returns layers array
- getLayers() - Method in class org.neuroph.util.Neuroph
-
- getLayersCount() - Method in class org.neuroph.core.NeuralNetwork
-
Returns number of layers in network
- getLearningRate() - Method in class org.neuroph.core.learning.IterativeLearning
-
Returns learning rate for this algorithm
- getLearningRate() - Method in class org.neuroph.nnet.learning.KohonenLearning
-
- getLearningRateChange() - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- getLearningRule() - Method in class org.neuroph.core.NeuralNetwork
-
Returns the learning algorithm of this network
- getLearningRules() - Method in class org.neuroph.util.Neuroph
-
- getLeftHigh() - Method in class org.neuroph.core.transfer.Trapezoid
-
Returns left high point of trapezoid function
- getLeftLow() - Method in class org.neuroph.core.transfer.Trapezoid
-
Returns left low point of trapezoid function
- getLog() - Method in class org.neuroph.nnet.learning.kmeans.KMeansClustering
-
- getLowLimit() - Method in class org.neuroph.util.data.norm.RangeNormalizer
-
- getMapDimensions() - Method in class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
Returns dimensions of feature maps in this layer
- getMapSize() - Method in class org.neuroph.nnet.learning.KohonenLearning
-
- getMatthewsCorrelationCoefficient() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
- getMax() - Method in class org.neuroph.util.DataSetStatistics
-
Get maximum for each data set column.
- getMaxDelta() - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- getMaxError() - Method in class org.neuroph.core.learning.SupervisedLearning
-
Returns learning error tolerance - the value of total network error to stop learning.
- getMaxIn() - Method in class org.neuroph.util.data.norm.DecimalScaleNormalizer
-
- getMaxIn() - Method in class org.neuroph.util.data.norm.MaxMinNormalizer
-
- getMaxIn() - Method in class org.neuroph.util.data.norm.RangeNormalizer
-
- getMaxIterations() - Method in class org.neuroph.core.learning.IterativeLearning
-
Returns max iterations limit of this learning algorithm
- getMaxIterations() - Method in class org.neuroph.nnet.comp.layer.CompetitiveLayer
-
Returns the maxIterations setting for this layer
- getMaxLearningRate() - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- getMaxMomentum() - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- getMaxOut() - Method in class org.neuroph.util.data.norm.DecimalScaleNormalizer
-
- getMaxOut() - Method in class org.neuroph.util.data.norm.MaxMinNormalizer
-
- getMaxOut() - Method in class org.neuroph.util.data.norm.RangeNormalizer
-
- getMaxTestTime() - Method in class org.neuroph.util.benchmark.BenchmarkTaskResults
-
- getMean() - Method in class org.neuroph.util.DataSetStatistics
-
Get mean for each data set column.
- getMeanSquareError() - Method in class org.neuroph.eval.Evaluation
-
- getMeanSquareError() - Method in class org.neuroph.eval.EvaluationResult
-
- getMin() - Method in class org.neuroph.util.DataSetStatistics
-
Get minimum for each data set column.
- getMinDelta() - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- getMinErrorChange() - Method in class org.neuroph.core.learning.SupervisedLearning
-
Returns min error change stopping criteria
- getMinErrorChangeIterationsCount() - Method in class org.neuroph.core.learning.SupervisedLearning
-
Returns number of iterations count for for min error change stopping criteria
- getMinErrorChangeIterationsLimit() - Method in class org.neuroph.core.learning.SupervisedLearning
-
Returns number of iterations for min error change stopping criteria
- getMinIn() - Method in class org.neuroph.util.data.norm.MaxMinNormalizer
-
- getMinIn() - Method in class org.neuroph.util.data.norm.RangeNormalizer
-
- getMinLearningRate() - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- getMinMomentum() - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- getMinOut() - Method in class org.neuroph.util.data.norm.MaxMinNormalizer
-
- getMinOut() - Method in class org.neuroph.util.data.norm.RangeNormalizer
-
- getMinTestTime() - Method in class org.neuroph.util.benchmark.BenchmarkTaskResults
-
- getMomentum() - Method in class org.neuroph.nnet.learning.MomentumBackpropagation
-
Returns the momentum factor
- getMomentumChange() - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- getName() - Method in class org.neuroph.util.benchmark.BenchmarkTask
-
Gets task name
- getName() - Method in class org.neuroph.util.plugins.PluginBase
-
Returns the name of this plugin
- getNetInput() - Method in class org.neuroph.core.Neuron
-
Returns total net input
- getNetwork() - Method in class org.neuroph.nnet.learning.SimulatedAnnealingLearning
-
Get the best network from the training.
- getNetworkType() - Method in class org.neuroph.core.NeuralNetwork
-
Returns type of this network
- getNeuralNet() - Method in class org.neuroph.eval.FoldResult
-
Returns neural network trained in this cross-validation fold.
- getNeuralNetwork() - Method in class org.neuroph.core.learning.LearningRule
-
Gets neural network
- getNeuralNetwork() - Method in class org.neuroph.eval.EvaluationResult
-
- getNeuronAt(int) - Method in class org.neuroph.core.Layer
-
Returns neuron at specified index position in this layer
- getNeuronAt(int, int) - Method in class org.neuroph.nnet.comp.layer.FeatureMapLayer
-
Returns neuron at specified position in this layer
- getNeuronAt(int, int, int) - Method in class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
Returns neuron instance at specified (x, y) position at specified feature map layer
- getNeuronOutput() - Method in class org.neuroph.eval.classification.ClassificationResult
-
- getNeurons() - Method in class org.neuroph.core.Layer
-
Returns array neurons in this layer as array
- getNeurons() - Method in class org.neuroph.util.Neuroph
-
- getNeuronsCount() - Method in class org.neuroph.core.Layer
-
Returns number of neurons in this layer
- getNeuronsCount() - Method in class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
Returns total number of neurons in all feature maps
- getNeuronType() - Method in class org.neuroph.util.NeuronProperties
-
- getNumberOfMaps() - Method in class org.neuroph.nnet.comp.layer.FeatureMapsLayer
-
Returns number of feature maps in this layer
- getOutConnections() - Method in class org.neuroph.core.Neuron
-
Returns output connections from this neuron
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.And
-
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.Difference
-
- getOutput(double[], double[]) - Method in class org.neuroph.core.input.Difference
-
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.EuclideanRBF
-
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.InputFunction
-
Returns ouput value of this input function for the given neuron inputs
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.Max
-
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.Min
-
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.Or
-
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.Product
-
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.Sum
-
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.SumSqr
-
- getOutput(List<Connection>) - Method in class org.neuroph.core.input.WeightedSum
-
- getOutput(double[], double[]) - Static method in class org.neuroph.core.input.WeightedSum
-
- getOutput() - Method in class org.neuroph.core.NeuralNetwork
-
Returns network output vector.
- getOutput() - Method in class org.neuroph.core.Neuron
-
Returns neuron's output
- getOutput(double) - Method in class org.neuroph.core.transfer.Gaussian
-
- getOutput(double) - Method in class org.neuroph.core.transfer.Linear
-
- getOutput(double) - Method in class org.neuroph.core.transfer.Log
-
- getOutput(double) - Method in class org.neuroph.core.transfer.Ramp
-
- getOutput(double) - Method in class org.neuroph.core.transfer.RectifiedLinear
-
- getOutput(double) - Method in class org.neuroph.core.transfer.Sgn
-
y = 1, x > 0
y = -1, x <= 0
- getOutput(double) - Method in class org.neuroph.core.transfer.Sigmoid
-
- getOutput(double) - Method in class org.neuroph.core.transfer.Sin
-
- getOutput(double) - Method in class org.neuroph.core.transfer.Step
-
- getOutput(double) - Method in class org.neuroph.core.transfer.Tanh
-
Returns the value of this function at x=input
- getOutput(double) - Method in class org.neuroph.core.transfer.TransferFunction
-
Returns the ouput of this function.
- getOutput(double) - Method in class org.neuroph.core.transfer.Trapezoid
-
- getOutput(int) - Method in class org.neuroph.nnet.comp.neuron.DelayedNeuron
-
Returns neuron output with the specified delay
- getOutput() - Method in class org.neuroph.nnet.comp.neuron.InputNeuron
-
- getOutputLabels() - Method in class org.neuroph.core.NeuralNetwork
-
- getOutputNeurons() - Method in class org.neuroph.core.NeuralNetwork
-
Returns output neurons
- getOutputsCount() - Method in class org.neuroph.core.NeuralNetwork
-
- getOutputSize() - Method in class org.neuroph.core.data.DataSet
-
Returns output vector size of training elements in this training set.
- getParentLayer() - Method in class org.neuroph.core.Neuron
-
Returns reference to parent layer for this neuron
- getParentNetwork() - Method in class org.neuroph.core.Layer
-
Returns reference to parent network
- getParentNetwork() - Method in class org.neuroph.util.plugins.PluginBase
-
Returns the parent network for this plugin
- getPlugin(Class<T>) - Method in class org.neuroph.core.NeuralNetwork
-
Returns the requested plugin
- getPoints() - Method in class org.neuroph.nnet.learning.kmeans.Cluster
-
- getPrecision() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
Calculate and return classification precision measure.
- getPreviousEpochError() - Method in class org.neuroph.core.learning.SupervisedLearning
-
Returns total network error in previous learning epoch
- getProperties() - Method in class org.neuroph.core.transfer.Sgn
-
Returns the properties of this function
- getProperties() - Method in class org.neuroph.core.transfer.Step
-
Returns the properties of this function
- getProperty(String) - Method in class org.neuroph.util.Properties
-
- getQ9() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
- getRandomGen() - Method in class org.neuroph.util.random.WeightsRandomizer
-
- getRecall() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
- getResult() - Method in class org.neuroph.eval.ClassifierEvaluator
-
- getResult() - Method in class org.neuroph.eval.ErrorEvaluator
-
- getResult() - Method in interface org.neuroph.eval.Evaluator
-
This method should return final evaluation result
- getResultsByFolds() - Method in class org.neuroph.eval.KFoldCrossValidation
-
- getRightHigh() - Method in class org.neuroph.core.transfer.Trapezoid
-
Returns right high point of trapezoid function
- getRightLow() - Method in class org.neuroph.core.transfer.Trapezoid
-
Returns right low point of trapezoid function
- getRowAt(int) - Method in class org.neuroph.core.data.DataSet
-
Returns training row at specified index position
- getRows() - Method in class org.neuroph.core.data.DataSet
-
Returns elements of this training set
- getSampling() - Method in class org.neuroph.eval.CrossValidationBak
-
- getScaleFactorIn() - Method in class org.neuroph.util.data.norm.DecimalScaleNormalizer
-
- getScaleFactorOut() - Method in class org.neuroph.util.data.norm.DecimalScaleNormalizer
-
- getSensitivity() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
Calculate and return classification sensitivity (recall, true positive rate)
number of correctly classified positive examples divided by the total number of actual positive examples
- getSigma() - Method in class org.neuroph.core.transfer.Gaussian
-
Returns the sigma parametar of this function
- getSlope() - Method in class org.neuroph.core.transfer.Linear
-
Returns the slope parametar of this function
- getSlope() - Method in class org.neuroph.core.transfer.Sigmoid
-
Returns the slope parametar of this function
- getSlope() - Method in class org.neuroph.core.transfer.Tanh
-
Returns the slope parameter of this function
- getSpecificity() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
Specifity , true negative rate
- getStandardDeviation() - Method in class org.neuroph.util.benchmark.BenchmarkTaskResults
-
- getStdDev() - Method in class org.neuroph.util.DataSetStatistics
-
Get standard deviation for each data set column.
- getTestIterations() - Method in class org.neuroph.util.benchmark.BenchmarkTask
-
Gets number of test (benchmarking) iterations
- getTestIterations() - Method in class org.neuroph.util.benchmark.BenchmarkTaskResults
-
- getThresh() - Method in class org.neuroph.nnet.comp.neuron.ThresholdNeuron
-
Returns threshold value for this neuron
- getThreshold() - Method in class org.neuroph.eval.ClassifierEvaluator
-
- getToNeuron() - Method in class org.neuroph.core.Connection
-
Gets to neuron for this connection
- getTotal() - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
Returns total number of classifications.
- getTotal() - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
- getTotalError() - Method in interface org.neuroph.core.learning.error.ErrorFunction
-
Return total network error
- getTotalError() - Method in class org.neuroph.core.learning.error.MeanAbsoluteError
-
- getTotalError() - Method in class org.neuroph.core.learning.error.MeanSquaredError
-
- getTotalNetworkError() - Method in class org.neuroph.core.learning.SupervisedLearning
-
- getTrainingData() - Method in class org.neuroph.core.Weight
-
Returns training data buffer for this weight
- getTrainingSet() - Method in class org.neuroph.core.learning.LearningRule
-
Gets training set
- getTrainingSet() - Method in class org.neuroph.eval.FoldResult
-
- getTransferFunction() - Method in class org.neuroph.core.Neuron
-
Returns transfer function
- getTransferFunction() - Method in class org.neuroph.util.NeuronProperties
-
- getTransferFunctionProperties() - Method in class org.neuroph.util.NeuronProperties
-
- getTransferFunctions() - Method in class org.neuroph.util.Neuroph
-
- getTrueNegative(int) - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
- getTruePositive(int) - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
- getTypeClass() - Method in enum org.neuroph.util.TransferFunctionType
-
- getTypeLabel() - Method in enum org.neuroph.util.NeuralNetworkType
-
- getTypeLabel() - Method in enum org.neuroph.util.TransferFunctionType
-
- getUseDynamicLearningRate() - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- getUseDynamicMomentum() - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- getValidationSet() - Method in class org.neuroph.eval.FoldResult
-
- getValue() - Method in class org.neuroph.core.Weight
-
Returns weight value
- getValueAt(int, int) - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
Returns value of confusion matrix at specified position
- getValueAt(int) - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
- getValues() - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
Returns confusion matrix values as double array
- getValues() - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
- getVar() - Method in class org.neuroph.util.DataSetStatistics
-
Get variant for each data set column.
- getVersion() - Static method in class org.neuroph.util.Neuroph
-
- getWarmupIterations() - Method in class org.neuroph.util.benchmark.BenchmarkTask
-
Gets number of warmup iterations.
- getWeight() - Method in class org.neuroph.core.Connection
-
Returns weight for this connection
- getWeightedInput() - Method in class org.neuroph.core.Connection
-
Returns the weighted input received through this connection
- getWeights() - Method in class org.neuroph.core.NeuralNetwork
-
Returns all network weights as an double array
- getWeights() - Method in class org.neuroph.core.Neuron
-
Returns weights vector of input connections
- getWeights() - Method in class org.neuroph.nnet.comp.Kernel
-
- getWidth() - Method in class org.neuroph.nnet.comp.Dimension2D
-
- getWidth() - Method in class org.neuroph.nnet.comp.Kernel
-
Returns width of this kernel
- getWidth() - Method in class org.neuroph.nnet.comp.layer.FeatureMapLayer
-
Returns width of this layer
- getWinner() - Method in class org.neuroph.nnet.comp.layer.CompetitiveLayer
-
Returns the winning neuron for this layer
- getXHigh() - Method in class org.neuroph.core.transfer.Ramp
-
Returns threshold value for the high output level
- getXLow() - Method in class org.neuroph.core.transfer.Ramp
-
Returns threshold value for the low output level
- getYHigh() - Method in class org.neuroph.core.transfer.Ramp
-
Returns output value for high output level
- getYHigh() - Method in class org.neuroph.core.transfer.Step
-
Returns output value for high output level
- getYLow() - Method in class org.neuroph.core.transfer.Ramp
-
Returns output value for low output level
- getYLow() - Method in class org.neuroph.core.transfer.Step
-
Returns output value for low output level
- gradient - Variable in class org.neuroph.nnet.learning.ResilientPropagation.ResilientWeightTrainingtData
-
- importFromFile(String, int, int, String) - Static method in class org.neuroph.util.TrainingSetImport
-
- inc(double) - Method in class org.neuroph.core.Weight
-
Increases the weight for the specified amount
- incrementElement(int, int) - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
Increments matrix value at specified position
- indexOf(Object) - Method in class org.neuroph.core.data.DataSet
-
- indexOf(Neuron) - Method in class org.neuroph.core.Layer
-
Returns the index position in layer for the specified neuron
- indexOf(Layer) - Method in class org.neuroph.core.NeuralNetwork
-
Returns index position of the specified layer
- initClusters() - Method in class org.neuroph.nnet.learning.kmeans.KMeansClustering
-
- initializeWeights(double) - Method in class org.neuroph.core.Layer
-
Initialize connection weights for the whole layer to to specified value
- initializeWeights(double) - Method in class org.neuroph.core.Neuron
-
Initialize weights for all input connections to specified value
- initWeights(double, double) - Method in class org.neuroph.nnet.comp.Kernel
-
- input - Variable in class org.neuroph.core.data.DataSetRow
-
Input vector for this training element
- InputAdapter - Interface in org.neuroph.util.io
-
Interface for reading neural network inputs from various data sources.
- inputConnections - Variable in class org.neuroph.core.Neuron
-
Collection of neuron's input connections (connections to this neuron)
- InputFunction - Class in org.neuroph.core.input
-
Neuron's input function.
- InputFunction() - Constructor for class org.neuroph.core.input.InputFunction
-
- inputFunction - Variable in class org.neuroph.core.Neuron
-
Input function for this neuron
- InputLayer - Class in org.neuroph.nnet.comp.layer
-
Represents a layer of input neurons - a typical neural network input layer
- InputLayer(int) - Constructor for class org.neuroph.nnet.comp.layer.InputLayer
-
Creates a new instance of InputLayer with specified number of input neurons
- InputMapsLayer - Class in org.neuroph.nnet.comp.layer
-
Input layer for convolutional networks
- InputMapsLayer(Dimension2D, int) - Constructor for class org.neuroph.nnet.comp.layer.InputMapsLayer
-
Create InputMapsLayer with specified number of maps with specified dimensions
- InputNeuron - Class in org.neuroph.nnet.comp.neuron
-
Provides input neuron behaviour - neuron with input extranaly set, which just
transfer that input to output without change.
- InputNeuron() - Constructor for class org.neuroph.nnet.comp.neuron.InputNeuron
-
Creates a new instance of InputNeuron with linear transfer function
- InputOutputNeuron - Class in org.neuroph.nnet.comp.neuron
-
Provides behaviour specific for neurons which act as input and the output
neurons within the same layer.
- InputOutputNeuron() - Constructor for class org.neuroph.nnet.comp.neuron.InputOutputNeuron
-
Creates an instance of neuron for Hopfield network
- InputOutputNeuron(InputFunction, TransferFunction) - Constructor for class org.neuroph.nnet.comp.neuron.InputOutputNeuron
-
Creates an instance of neuron for Hopfield network with specified input
and transfer functions
- inputsMax(DataSet) - Static method in class org.neuroph.util.DataSetStats
-
- inputsMean(DataSet) - Static method in class org.neuroph.util.DataSetStats
-
- inputsMin(DataSet) - Static method in class org.neuroph.util.DataSetStats
-
- inputsStandardDeviation(DataSet, double[]) - Static method in class org.neuroph.util.DataSetStats
-
- InputStreamAdapter - Class in org.neuroph.util.io
-
Implementation of InputAdapter interface for reading neural network inputs from input stream.
- InputStreamAdapter(InputStream) - Constructor for class org.neuroph.util.io.InputStreamAdapter
-
- InputStreamAdapter(BufferedReader) - Constructor for class org.neuroph.util.io.InputStreamAdapter
-
- Instar - Class in org.neuroph.nnet
-
Instar neural network with Instar learning rule.
- Instar(int) - Constructor for class org.neuroph.nnet.Instar
-
Creates new Instar with specified number of input neurons.
- InstarLearning - Class in org.neuroph.nnet.learning
-
Hebbian-like learning rule for Instar network.
- InstarLearning() - Constructor for class org.neuroph.nnet.learning.InstarLearning
-
Creates new instance of InstarLearning algorithm
- IOHelper - Class in org.neuroph.util.io
-
This class is helper for feeding neural network with data using some InputAdapter
and writing network output using OutputAdapter
- IOHelper() - Constructor for class org.neuroph.util.io.IOHelper
-
- isBatchMode() - Method in class org.neuroph.core.learning.SupervisedLearning
-
Returns true if learning is performed in batch mode, false otherwise
- isCompeting() - Method in class org.neuroph.nnet.comp.neuron.CompetitiveNeuron
-
Retruns true if this neuron is in competing mode, false otherwise
- isEmpty() - Method in class org.neuroph.core.data.DataSet
-
Returns true if training set is empty, false otherwise
- isEmpty() - Method in class org.neuroph.core.Layer
-
- isEmpty() - Method in class org.neuroph.core.NeuralNetwork
-
- isIterationsLimited() - Method in class org.neuroph.core.learning.IterativeLearning
-
- isPausedLearning() - Method in class org.neuroph.core.learning.IterativeLearning
-
Returns true if learning thread is paused, false otherwise
- isReached() - Method in class org.neuroph.core.learning.stop.MaxErrorStop
-
- isReached() - Method in class org.neuroph.core.learning.stop.MaxIterationsStop
-
- isReached() - Method in class org.neuroph.core.learning.stop.SmallErrorChangeStop
-
- isReached() - Method in interface org.neuroph.core.learning.stop.StopCondition
-
Returns true if learning rule should stop, false otherwise
- isStopped() - Method in class org.neuroph.core.learning.LearningRule
-
Returns true if learning has stopped, false otherwise
- isSupervised() - Method in class org.neuroph.core.data.DataSet
-
Returns true if data set is supervised, false otherwise
- isSupervised() - Method in class org.neuroph.core.data.DataSetRow
-
- IterativeLearning - Class in org.neuroph.core.learning
-
Base class for all iterative learning algorithms.
- IterativeLearning() - Constructor for class org.neuroph.core.learning.IterativeLearning
-
Creates new instance of IterativeLearning learning algorithm
- iterator() - Method in class org.neuroph.core.data.BufferedDataSet
-
Returns iterator for buffered data set
- iterator() - Method in class org.neuroph.core.data.DataSet
-
Returns Iterator for iterating training elements collection
- iterator() - Method in class org.neuroph.core.Layer
-
- label - Variable in class org.neuroph.core.data.DataSetRow
-
Label for this training element
- Layer - Class in org.neuroph.core
-
Layer of neurons in a neural network.
- Layer() - Constructor for class org.neuroph.core.Layer
-
Creates an instance of empty Layer
- Layer(int) - Constructor for class org.neuroph.core.Layer
-
Creates an instance of empty Layer for specified number of neurons
- Layer(int, NeuronProperties) - Constructor for class org.neuroph.core.Layer
-
Creates an instance of Layer with the specified number of neurons with
specified neuron properties
- LayerFactory - Class in org.neuroph.util
-
Provides methods to create instance of a Layer with various setting (number of neurons and neuron's properties, etc.
- learn(DataSet) - Method in class org.neuroph.core.learning.IterativeLearning
-
- learn(DataSet, int) - Method in class org.neuroph.core.learning.IterativeLearning
-
Trains network for the specified training set and number of iterations
- learn(DataSet) - Method in class org.neuroph.core.learning.LearningRule
-
Override this method to implement specific learning procedures
- learn(DataSet, double) - Method in class org.neuroph.core.learning.SupervisedLearning
-
Trains network for the specified training set and maxError
- learn(DataSet, double, int) - Method in class org.neuroph.core.learning.SupervisedLearning
-
Trains network for the specified training set, maxError and number of iterations
- learn(DataSet) - Method in class org.neuroph.core.NeuralNetwork
-
Learn the specified training set
- learn(DataSet, L) - Method in class org.neuroph.core.NeuralNetwork
-
Learn the specified training set, using specified learning rule
- learn(DataSet) - Method in class org.neuroph.nnet.learning.HopfieldLearning
-
Calculates weights for the hopfield net to learn the specified training
set
- learn(DataSet) - Method in class org.neuroph.nnet.learning.KohonenLearning
-
- LEARNING_STOPPED - Static variable in class org.neuroph.core.events.LearningEvent
-
- LearningEvent - Class in org.neuroph.core.events
-
This class holds information about the source and type of learning event.
- LearningEvent(LearningRule, LearningEvent.Type) - Constructor for class org.neuroph.core.events.LearningEvent
-
- LearningEvent.Type - Enum in org.neuroph.core.events
-
- LearningEventListener - Interface in org.neuroph.core.events
-
This interface is implemented by classes who are listening to learning events (iterations, error etc.)
LearningEvent class holds the information about event.
- learningRate - Variable in class org.neuroph.core.learning.IterativeLearning
-
Learning rate parametar
- LearningRule - Class in org.neuroph.core.learning
-
Base class for all neural network learning algorithms.
- LearningRule() - Constructor for class org.neuroph.core.learning.LearningRule
-
Creates new instance of learning rule
- learnPattern(DataSetRow) - Method in class org.neuroph.core.learning.SupervisedLearning
-
Trains network with the input and desired output pattern from the specified training element
- learnPattern(DataSetRow) - Method in class org.neuroph.core.learning.UnsupervisedLearning
-
Trains network with the pattern from the specified training element
- Linear - Class in org.neuroph.core.transfer
-
Linear neuron transfer function.
- Linear() - Constructor for class org.neuroph.core.transfer.Linear
-
Creates an instance of Linear transfer function
- Linear(double) - Constructor for class org.neuroph.core.transfer.Linear
-
Creates an instance of Linear transfer function with specified value
for getSlope parametar.
- Linear(Properties) - Constructor for class org.neuroph.core.transfer.Linear
-
Creates an instance of Linear transfer function with specified properties
- listeners - Variable in class org.neuroph.core.learning.LearningRule
-
List of learning rule listeners
- LMS - Class in org.neuroph.nnet.learning
-
LMS learning rule for neural networks.
- LMS() - Constructor for class org.neuroph.nnet.learning.LMS
-
Creates a new LMS learning rule
- load(String) - Static method in class org.neuroph.core.data.DataSet
-
Loads training set from the specified file
TODO: throw checked exceptionse here
- load(String) - Static method in class org.neuroph.core.NeuralNetwork
-
- load(InputStream) - Static method in class org.neuroph.core.NeuralNetwork
-
Loads neural network from the specified InputStream.
- Log - Class in org.neuroph.core.transfer
-
Log neuron transfer function.
- Log() - Constructor for class org.neuroph.core.transfer.Log
-
- network2array(NeuralNetwork, double[]) - Static method in class org.neuroph.util.NeuralNetworkCODEC
-
Encode a network to an array.
- neuralNetwork - Variable in class org.neuroph.core.learning.LearningRule
-
Neural network to train
- NeuralNetwork<L extends LearningRule> - Class in org.neuroph.core
-
Base class for artificial neural networks.
- NeuralNetwork() - Constructor for class org.neuroph.core.NeuralNetwork
-
Creates an instance of empty neural network.
- NeuralNetworkCODEC - Class in org.neuroph.util
-
A CODEC encodes and decodes neural networks, much like the more standard
definition of a CODEC encodes and decodes audio/video.
- NeuralNetworkEvent - Class in org.neuroph.core.events
-
This class holds information about the source and type of some neural network event.
- NeuralNetworkEvent(NeuralNetwork, NeuralNetworkEvent.Type) - Constructor for class org.neuroph.core.events.NeuralNetworkEvent
-
- NeuralNetworkEvent(Layer, NeuralNetworkEvent.Type) - Constructor for class org.neuroph.core.events.NeuralNetworkEvent
-
- NeuralNetworkEvent(Neuron, NeuralNetworkEvent.Type) - Constructor for class org.neuroph.core.events.NeuralNetworkEvent
-
- NeuralNetworkEvent.Type - Enum in org.neuroph.core.events
-
Types of neural network events
- NeuralNetworkEventListener - Interface in org.neuroph.core.events
-
This interface is implemented by classes who are listening to neural network events events (to be defined)
NeuralNetworkEvent class holds the information about event.
- NeuralNetworkFactory - Class in org.neuroph.util
-
Provides methods to create various neural networks.
- NeuralNetworkFactory() - Constructor for class org.neuroph.util.NeuralNetworkFactory
-
- NeuralNetworkType - Enum in org.neuroph.util
-
Contains neural network types and labels.
- NeuroFuzzyPerceptron - Class in org.neuroph.nnet
-
The NeuroFuzzyReasoner class represents Neuro Fuzzy Reasoner architecture.
- NeuroFuzzyPerceptron(double[][], double[][]) - Constructor for class org.neuroph.nnet.NeuroFuzzyPerceptron
-
- NeuroFuzzyPerceptron(int, Vector<Integer>, int) - Constructor for class org.neuroph.nnet.NeuroFuzzyPerceptron
-
- Neuron - Class in org.neuroph.core
-
Basic general neuron model according to McCulloch-Pitts neuron model.
- Neuron() - Constructor for class org.neuroph.core.Neuron
-
Creates an instance of Neuron with default settings: weighted sum input
function and Step transfer function.
- Neuron(InputFunction, TransferFunction) - Constructor for class org.neuroph.core.Neuron
-
Creates an instance of Neuron with the specified input and transfer
functions.
- NeuronFactory - Class in org.neuroph.util
-
Provides methods to create customized instances of Neuron.
- NeuronProperties - Class in org.neuroph.util
-
Represents properties of a neuron.
- NeuronProperties() - Constructor for class org.neuroph.util.NeuronProperties
-
- NeuronProperties(Class<? extends Neuron>) - Constructor for class org.neuroph.util.NeuronProperties
-
- NeuronProperties(Class<? extends Neuron>, Class<? extends TransferFunction>) - Constructor for class org.neuroph.util.NeuronProperties
-
- NeuronProperties(Class<? extends Neuron>, Class<? extends InputFunction>, Class<? extends TransferFunction>) - Constructor for class org.neuroph.util.NeuronProperties
-
- NeuronProperties(Class<? extends Neuron>, TransferFunctionType) - Constructor for class org.neuroph.util.NeuronProperties
-
- NeuronProperties(TransferFunctionType, boolean) - Constructor for class org.neuroph.util.NeuronProperties
-
- neurons - Variable in class org.neuroph.core.Layer
-
Collection of neurons in this layer
- Neuroph - Class in org.neuroph.util
-
This singleton holds global settings for the whole framework
- Neuroph() - Constructor for class org.neuroph.util.Neuroph
-
- NeurophException - Exception in org.neuroph.core.exceptions
-
Base exception type for Neuroph.
- NeurophException() - Constructor for exception org.neuroph.core.exceptions.NeurophException
-
Default constructor.
- NeurophException(String) - Constructor for exception org.neuroph.core.exceptions.NeurophException
-
Construct a message exception.
- NeurophException(Throwable) - Constructor for exception org.neuroph.core.exceptions.NeurophException
-
Construct an exception that holds another exception.
- NeurophException(String, Throwable) - Constructor for exception org.neuroph.core.exceptions.NeurophException
-
Construct an exception that holds another exception.
- NeurophInputException - Exception in org.neuroph.util.io
-
This exception is thrown when error occurs when reading input using some InputAdapter
- NeurophInputException() - Constructor for exception org.neuroph.util.io.NeurophInputException
-
Constructs an NeurophInputException with no detail message.
- NeurophInputException(String) - Constructor for exception org.neuroph.util.io.NeurophInputException
-
Constructs an NeurophInputException with the specified detail message.
- NeurophInputException(String, Throwable) - Constructor for exception org.neuroph.util.io.NeurophInputException
-
Constructs a NeurophInputException with the specified detail message and specified cause.
- NeurophInputException(Throwable) - Constructor for exception org.neuroph.util.io.NeurophInputException
-
Constructs a new runtime exception with the specified cause
- NeurophOutputException - Exception in org.neuroph.util.io
-
This exception is thrown when some error occurs when writing neural network
output using some output adapter.
- NeurophOutputException() - Constructor for exception org.neuroph.util.io.NeurophOutputException
-
Constructs an NeurophOutputException with no detail message.
- NeurophOutputException(String) - Constructor for exception org.neuroph.util.io.NeurophOutputException
-
Constructs an NeurophOutputException with the specified detail message.
- NeurophOutputException(String, Throwable) - Constructor for exception org.neuroph.util.io.NeurophOutputException
-
Constructs a NeurophOutputException with the specified detail message and specified cause.
- NeurophOutputException(Throwable) - Constructor for exception org.neuroph.util.io.NeurophOutputException
-
Constructs a new runtime exception with the specified cause
- next() - Method in class org.neuroph.core.data.BufferedDataSet
-
Returns next data set row.
- nextRandomWeight() - Method in class org.neuroph.util.random.GaussianRandomizer
-
- nextRandomWeight() - Method in class org.neuroph.util.random.RangeRandomizer
-
Generates next random value within [min, max] range determined by the settings in this randomizer
- nextRandomWeight() - Method in class org.neuroph.util.random.WeightsRandomizer
-
Returns next random value from random generator, that will be used to initialize weight
Override this method to implement custom random number generators
- NguyenWidrowRandomizer - Class in org.neuroph.util.random
-
This class provides NguyenWidrow randmization technique, which gives very good results
for Multi Layer Perceptrons trained with back propagation family of learning rules.
- NguyenWidrowRandomizer(double, double) - Constructor for class org.neuroph.util.random.NguyenWidrowRandomizer
-
- normalize(DataSet) - Method in class org.neuroph.util.data.norm.DecimalScaleNormalizer
-
- normalize(DataSet) - Method in class org.neuroph.util.data.norm.MaxMinNormalizer
-
- normalize(DataSet) - Method in class org.neuroph.util.data.norm.MaxNormalizer
-
- normalize(DataSet) - Method in interface org.neuroph.util.data.norm.Normalizer
-
Normalize specified data set
- normalize(DataSet) - Method in class org.neuroph.util.data.norm.RangeNormalizer
-
- normalize(DataSet) - Method in class org.neuroph.util.data.norm.ZeroMeanNormalizer
-
- normalizeMax(DataSet) - Static method in class org.neuroph.core.data.DataSets
-
- Normalizer - Interface in org.neuroph.util.data.norm
-
Interface for data set normalization methods.
- OjaLearning - Class in org.neuroph.nnet.learning
-
Oja learning rule wich is a modification of unsupervised hebbian learning.
- OjaLearning() - Constructor for class org.neuroph.nnet.learning.OjaLearning
-
Creates an instance of OjaLearning algorithm
- onStart() - Method in class org.neuroph.core.learning.IterativeLearning
-
This method is executed when learning starts, before the first epoch.
- onStart() - Method in class org.neuroph.core.learning.LearningRule
-
Prepares the learning rule to run by setting stop flag to false
If you override this method make sure you call parent method first
- onStart() - Method in class org.neuroph.core.learning.SupervisedLearning
-
- onStart() - Method in class org.neuroph.nnet.learning.MomentumBackpropagation
-
- onStart() - Method in class org.neuroph.nnet.learning.QuickPropagation
-
- onStart() - Method in class org.neuroph.nnet.learning.RBFLearning
-
- onStart() - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- onStop() - Method in class org.neuroph.core.learning.LearningRule
-
Invoked after the learning has stopped
- Or - Class in org.neuroph.core.input
-
Performs logic OR operation on input vector.
- Or() - Constructor for class org.neuroph.core.input.Or
-
- org.neuroph.core - package org.neuroph.core
-
Provides base classes and basic building components for neural networks.
- org.neuroph.core.data - package org.neuroph.core.data
-
Provides data set related classes and manipulation methods.
- org.neuroph.core.events - package org.neuroph.core.events
-
Provides neural network learning events system
- org.neuroph.core.exceptions - package org.neuroph.core.exceptions
-
Provides specific exceptions when working with neural networks
- org.neuroph.core.input - package org.neuroph.core.input
-
Provides common neuron input functions
- org.neuroph.core.learning - package org.neuroph.core.learning
-
Provides base classes for neural network learning algorithms.
- org.neuroph.core.learning.error - package org.neuroph.core.learning.error
-
Provides error functions for learning rules
- org.neuroph.core.learning.stop - package org.neuroph.core.learning.stop
-
Provides stop functions for learning rules
- org.neuroph.core.transfer - package org.neuroph.core.transfer
-
Provides common neuron transfer functions
- org.neuroph.eval - package org.neuroph.eval
-
- org.neuroph.eval.classification - package org.neuroph.eval.classification
-
- org.neuroph.nnet - package org.neuroph.nnet
-
Provides out-of-the-box neural networks
- org.neuroph.nnet.comp - package org.neuroph.nnet.comp
-
Provides components for the specific neural network models.
- org.neuroph.nnet.comp.layer - package org.neuroph.nnet.comp.layer
-
Provides various specific layer types
- org.neuroph.nnet.comp.neuron - package org.neuroph.nnet.comp.neuron
-
Provides various specific neuron types
- org.neuroph.nnet.learning - package org.neuroph.nnet.learning
-
Provides implementations of specific neural network learning algorithms.
- org.neuroph.nnet.learning.kmeans - package org.neuroph.nnet.learning.kmeans
-
- org.neuroph.nnet.learning.knn - package org.neuroph.nnet.learning.knn
-
- org.neuroph.util - package org.neuroph.util
-
Provides various utility classes for creating neural networks,
type codes, parsing vectors, etc.
- org.neuroph.util.benchmark - package org.neuroph.util.benchmark
-
Provides microbenchmaarking framework for measuring and comparing Neuroph performance.
- org.neuroph.util.data.norm - package org.neuroph.util.data.norm
-
Provides data normalization techniques.
- org.neuroph.util.data.sample - package org.neuroph.util.data.sample
-
Provides data sampling techniques
- org.neuroph.util.io - package org.neuroph.util.io
-
Provides input/output adapters for file, JDBC, URL, stream
- org.neuroph.util.plugins - package org.neuroph.util.plugins
-
Provides various plugins for neural networks.
- org.neuroph.util.random - package org.neuroph.util.random
-
Provides weights randomization techniques
- outConnections - Variable in class org.neuroph.core.Neuron
-
Collection of neuron's output connections (connections from this to other
neurons)
- output - Variable in class org.neuroph.core.Neuron
-
Neuron output
- output - Variable in class org.neuroph.core.transfer.TransferFunction
-
Output result
- OutputAdapter - Interface in org.neuroph.util.io
-
Interface for writing neural network outputs to some destination.
- outputBuffer - Variable in class org.neuroph.core.NeuralNetwork
-
Neural network output buffer
- outputHistory - Variable in class org.neuroph.nnet.comp.neuron.DelayedNeuron
-
Output history for this neuron
- OutputStreamAdapter - Class in org.neuroph.util.io
-
Implementation of OutputAdapter interface for writing neural network outputs to output stream.
- OutputStreamAdapter(OutputStream) - Constructor for class org.neuroph.util.io.OutputStreamAdapter
-
Creates a new OutputStreamAdapter for specified output stream.
- OutputStreamAdapter(BufferedWriter) - Constructor for class org.neuroph.util.io.OutputStreamAdapter
-
Creates a new OutputStreamAdapter for specified BufferedWriter.
- Outstar - Class in org.neuroph.nnet
-
Outstar neural network with Outstar learning rule.
- Outstar(int) - Constructor for class org.neuroph.nnet.Outstar
-
Creates an instance of Outstar network with specified number of neurons
in output layer.
- OutstarLearning - Class in org.neuroph.nnet.learning
-
Hebbian-like learning rule for Outstar network.
- OutstarLearning() - Constructor for class org.neuroph.nnet.learning.OutstarLearning
-
Creates new instance of OutstarLearning algorithm
- Ramp - Class in org.neuroph.core.transfer
-
Ramp neuron transfer function.
- Ramp() - Constructor for class org.neuroph.core.transfer.Ramp
-
Creates an instance of Ramp transfer function with default settings
- Ramp(double, double, double, double, double) - Constructor for class org.neuroph.core.transfer.Ramp
-
Creates an instance of Ramp transfer function with specified settings
- Ramp(Properties) - Constructor for class org.neuroph.core.transfer.Ramp
-
Creates an instance of Ramp transfer function with specified properties.
- randomGen - Variable in class org.neuroph.util.random.WeightsRandomizer
-
Random number genarator used to generate random values for weights
- randomize(double, double) - Method in class org.neuroph.core.Weight
-
Deprecated.
- randomize(double) - Method in class org.neuroph.nnet.learning.SimulatedAnnealingLearning
-
Randomize the weights and thresholds.
- randomize(Neuron) - Method in class org.neuroph.util.random.DistortRandomizer
-
Iterate all layers, neurons and connection weight and apply distort randomization
- randomize(Neuron) - Method in class org.neuroph.util.random.HeZhangRenSunUniformWeightsRandomizer
-
"He" uniform distribution [-limit, limit] where limit is 3 * sqrt(2 / fan in)
- randomize(NeuralNetwork) - Method in class org.neuroph.util.random.NguyenWidrowRandomizer
-
- randomize(NeuralNetwork<?>) - Method in class org.neuroph.util.random.WeightsRandomizer
-
Iterates and randomizes all layers in specified network
- randomize(Layer) - Method in class org.neuroph.util.random.WeightsRandomizer
-
Iterate and randomizes all neurons in specified layer
- randomize(Neuron) - Method in class org.neuroph.util.random.WeightsRandomizer
-
Iterates and randomizes all connection weights in specified neuron
- randomizeWeights() - Method in class org.neuroph.core.NeuralNetwork
-
Randomizes connection weights for the whole network
- randomizeWeights(double, double) - Method in class org.neuroph.core.NeuralNetwork
-
Randomizes connection weights for the whole network within specified
value range
- randomizeWeights(Random) - Method in class org.neuroph.core.NeuralNetwork
-
Randomizes connection weights for the whole network using specified
random generator
- randomizeWeights(WeightsRandomizer) - Method in class org.neuroph.core.NeuralNetwork
-
Randomizes connection weights for the whole network using specified
randomizer
- RangeNormalizer - Class in org.neuroph.util.data.norm
-
Performs normalization of a data set inputs and outputs to specified range.
- RangeNormalizer(double, double) - Constructor for class org.neuroph.util.data.norm.RangeNormalizer
-
- RangeRandomizer - Class in org.neuroph.util.random
-
This class provides ranged weights randomizer, which randomize weights in specified [min, max] range.
- RangeRandomizer(double, double) - Constructor for class org.neuroph.util.random.RangeRandomizer
-
Creates a new instance of RangeRandomizer within specified .
- RangeRandomizer(double, double, Random) - Constructor for class org.neuroph.util.random.RangeRandomizer
-
- RBFLearning - Class in org.neuroph.nnet.learning
-
Learning rule for Radial Basis Function networks.
- RBFLearning() - Constructor for class org.neuroph.nnet.learning.RBFLearning
-
- RBFNetwork - Class in org.neuroph.nnet
-
Radial basis function neural network.
- RBFNetwork(int, int, int) - Constructor for class org.neuroph.nnet.RBFNetwork
-
Creates new RBFNetwork with specified number of neurons in input, rbf and output layer
- readFromCsv(String, int, int, String) - Static method in class org.neuroph.core.data.DataSets
-
- readFromCsv(String, int, int) - Static method in class org.neuroph.core.data.DataSets
-
- readInput() - Method in interface org.neuroph.util.io.InputAdapter
-
Reads input from data source and returns input for neural network as array of doubles.
- readInput() - Method in class org.neuroph.util.io.InputStreamAdapter
-
- readInput() - Method in class org.neuroph.util.io.JDBCInputAdapter
-
Reads next row from result set and returns input for neural network as array of doubles.
- recall - Variable in class org.neuroph.eval.classification.ClassificationMetrics.Stats
-
- RectifiedLinear - Class in org.neuroph.core.transfer
-
- RectifiedLinear() - Constructor for class org.neuroph.core.transfer.RectifiedLinear
-
- RectifierNeuralNetwork - Class in org.neuroph.nnet
-
- RectifierNeuralNetwork(List<Integer>) - Constructor for class org.neuroph.nnet.RectifierNeuralNetwork
-
- remove() - Method in class org.neuroph.core.data.BufferedDataSet
-
- remove(Object) - Method in class org.neuroph.core.data.DataSet
-
- remove(int) - Method in class org.neuroph.core.data.DataSet
-
- removeAllConnections() - Method in class org.neuroph.core.Neuron
-
- removeAllInputConnections() - Method in class org.neuroph.core.Neuron
-
- removeAllNeurons() - Method in class org.neuroph.core.Layer
-
- removeAllOutputConnections() - Method in class org.neuroph.core.Neuron
-
- removeInputConnection(Connection) - Method in class org.neuroph.core.Neuron
-
- removeInputConnectionFrom(Neuron) - Method in class org.neuroph.core.Neuron
-
Removes input connection which is connected to specified neuron
- removeLayer(Layer) - Method in class org.neuroph.core.NeuralNetwork
-
Removes specified layer from network
- removeLayerAt(int) - Method in class org.neuroph.core.NeuralNetwork
-
Removes layer at specified index position from net
- removeListener(LearningEventListener) - Method in class org.neuroph.core.learning.LearningRule
-
- removeListener(NeuralNetworkEventListener) - Method in class org.neuroph.core.NeuralNetwork
-
- removeNeuron(Neuron) - Method in class org.neuroph.core.Layer
-
Removes neuron from layer
- removeNeuronAt(int) - Method in class org.neuroph.core.Layer
-
Removes neuron at specified index position in this layer
- removeOutputConnection(Connection) - Method in class org.neuroph.core.Neuron
-
- removeOutputConnectionTo(Neuron) - Method in class org.neuroph.core.Neuron
-
- removePlugin(Class) - Method in class org.neuroph.core.NeuralNetwork
-
Removes the plugin with specified name
- removePoint(KVector) - Method in class org.neuroph.nnet.learning.kmeans.Cluster
-
- removeRowAt(int) - Method in class org.neuroph.core.data.DataSet
-
Removes training row at specified index position
- reset() - Method in class org.neuroph.core.Layer
-
Resets the activation and input levels for all neurons in this layer
- reset() - Method in interface org.neuroph.core.learning.error.ErrorFunction
-
Sets total error and pattern count to zero.
- reset() - Method in class org.neuroph.core.learning.error.MeanAbsoluteError
-
- reset() - Method in class org.neuroph.core.learning.error.MeanSquaredError
-
- reset() - Method in class org.neuroph.core.NeuralNetwork
-
Resets the activation levels for whole network
- reset() - Method in class org.neuroph.core.Neuron
-
Sets input and output activation levels to zero
- reset() - Method in class org.neuroph.eval.ClassifierEvaluator
-
- reset() - Method in class org.neuroph.eval.ErrorEvaluator
-
- reset() - Method in interface org.neuroph.eval.Evaluator
-
- reset() - Method in class org.neuroph.nnet.comp.neuron.CompetitiveNeuron
-
Resets the input, output and mode for this neuron
- reset() - Method in class org.neuroph.util.benchmark.Stopwatch
-
Resets the stopwatch (clears start and stop time)
- ResilientPropagation - Class in org.neuroph.nnet.learning
-
Resilient Propagation learning rule used for Multi Layer Perceptron neural networks.
- ResilientPropagation() - Constructor for class org.neuroph.nnet.learning.ResilientPropagation
-
- ResilientPropagation.ResilientWeightTrainingtData - Class in org.neuroph.nnet.learning
-
- ResilientWeightTrainingtData() - Constructor for class org.neuroph.nnet.learning.ResilientPropagation.ResilientWeightTrainingtData
-
- resillientWeightUpdate(Weight) - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
Weight update by done by ResilientPropagation learning rule
Executed at the end of epoch (in batch mode)
- resume() - Method in class org.neuroph.core.learning.IterativeLearning
-
Resumes the paused learning
- resumeLearning() - Method in class org.neuroph.core.NeuralNetwork
-
Resumes paused learning - notifies the learning rule to continue
- run() - Method in class org.neuroph.eval.CrossValidationBak
-
- run() - Method in class org.neuroph.eval.KFoldCrossValidation
-
- run() - Method in class org.neuroph.util.benchmark.Benchmark
-
Runs all benchmark tasks
- runFullEvaluation(NeuralNetwork<?>, DataSet) - Static method in class org.neuroph.eval.Evaluation
-
Out of the box method (util) which computes all metrics for given neural network and test data set
- runTask(BenchmarkTask) - Static method in class org.neuroph.util.benchmark.Benchmark
-
Runs specified benchmark tasks, the basic benchmarking workflow.
- runTest() - Method in class org.neuroph.util.benchmark.BenchmarkTask
-
This method should hold the code to benchmark
- runTest() - Method in class org.neuroph.util.benchmark.MyBenchmarkTask
-
- sample(Sampling) - Method in class org.neuroph.core.data.DataSet
-
- sample(DataSet) - Method in interface org.neuroph.util.data.sample.Sampling
-
- sample(DataSet) - Method in class org.neuroph.util.data.sample.SubSampling
-
- Sampling - Interface in org.neuroph.util.data.sample
-
Interface for data set sampling methods.
- save(String) - Method in class org.neuroph.core.data.DataSet
-
Saves this training set to the specified file
- save() - Method in class org.neuroph.core.data.DataSet
-
Saves this training set to file specified in its filePath field
- save(String) - Method in class org.neuroph.core.NeuralNetwork
-
Saves neural network into the specified file.
- saveAsTxt(String, String) - Method in class org.neuroph.core.data.DataSet
-
- setAmplitude(double) - Method in class org.neuroph.core.transfer.Tanh
-
Sets the slope parameter for this function
- setBatchMode(boolean) - Method in class org.neuroph.core.learning.SupervisedLearning
-
Sets batch mode on/off (true/false)
- setBatchMode(boolean) - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- setBias(double) - Method in class org.neuroph.nnet.comp.neuron.InputOutputNeuron
-
Sets bias value for this neuron
- setCentroid(KVector) - Method in class org.neuroph.nnet.learning.kmeans.Cluster
-
- setClassLabel(String) - Method in class org.neuroph.eval.classification.ClassificationMetrics
-
- setCluster(Cluster) - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
- setColumnName(int, String) - Method in class org.neuroph.core.data.DataSet
-
- setColumnNames(String[]) - Method in class org.neuroph.core.data.DataSet
-
- setColumnType(int, DataSetColumnType) - Method in class org.neuroph.core.data.DataSet
-
Sets column type for the given index.
- setConfusionMatrix(ConfusionMatrix) - Method in class org.neuroph.eval.EvaluationResult
-
- setConfusionMatrix(ConfusionMatrix) - Method in class org.neuroph.eval.FoldResult
-
- setDataSet(DataSet) - Method in class org.neuroph.eval.EvaluationResult
-
- setDataSet(DataSet) - Method in class org.neuroph.nnet.learning.kmeans.KMeansClustering
-
- setDataSet(List<KVector>) - Method in class org.neuroph.nnet.learning.knn.KNearestNeighbour
-
- setDecreaseFactor(double) - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- setDefaultIO(NeuralNetwork) - Static method in class org.neuroph.util.NeuralNetworkFactory
-
Sets default input and output neurons for network (first layer as input,
last as output)
- setDelay(int) - Method in class org.neuroph.nnet.comp.DelayedConnection
-
Sets delay value for this connection
- setDelta(double) - Method in class org.neuroph.core.Neuron
-
Sets delta for this neuron.
- setDesiredOutput(double[]) - Method in class org.neuroph.core.data.DataSetRow
-
- setDistance(double) - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
- setErrorCorrection(double) - Method in class org.neuroph.nnet.learning.BinaryDeltaRule
-
Sets the errorCorrection parametar
- setErrorFunction(ErrorFunction) - Method in class org.neuroph.core.learning.SupervisedLearning
-
- setFilePath(String) - Method in class org.neuroph.core.data.DataSet
-
Sets full file path for this training set
- setFlattenNetworks(boolean) - Method in class org.neuroph.util.Neuroph
-
Turn on/off flat networ support from Encog
- setHeight(int) - Method in class org.neuroph.nnet.comp.Dimension2D
-
- setHeight(int) - Method in class org.neuroph.nnet.comp.Kernel
-
Sets height of this kernel
- setIncreaseFactor(double) - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- setInitialDelta(double) - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- setInput(double[]) - Method in class org.neuroph.core.data.DataSetRow
-
Sets input vector
- setInput(double...) - Method in class org.neuroph.core.NeuralNetwork
-
Sets network input.
- setInput(double) - Method in class org.neuroph.core.Neuron
-
Sets neuron's input
- setInput(double) - Method in class org.neuroph.nnet.comp.neuron.InputOutputNeuron
-
Sets total net input for this cell
- setInput(double...) - Method in class org.neuroph.nnet.ConvolutionalNetwork
-
Sets network input, to all feature maps in input layer
- setInputFunction(InputFunction) - Method in class org.neuroph.core.Neuron
-
Sets input function
- setInputNeurons(List<Neuron>) - Method in class org.neuroph.core.NeuralNetwork
-
Sets input neurons
- setIsCompeting(boolean) - Method in class org.neuroph.nnet.comp.neuron.CompetitiveNeuron
-
Sets the flag to indicate that this neuron is in competing mode
- setIterations(int, int) - Method in class org.neuroph.nnet.learning.KohonenLearning
-
- setLabel(String) - Method in class org.neuroph.core.data.DataSet
-
Sets label for this training set
- setLabel(String) - Method in class org.neuroph.core.data.DataSetRow
-
Set training element label
- setLabel(String) - Method in class org.neuroph.core.Layer
-
Set layer label
- setLabel(String) - Method in class org.neuroph.core.NeuralNetwork
-
Set network label
- setLabel(String) - Method in class org.neuroph.core.Neuron
-
Sets the label for this neuron
- setLearningRate(double) - Method in class org.neuroph.core.learning.IterativeLearning
-
Sets learning rate for this algorithm
- setLearningRate(double) - Method in class org.neuroph.nnet.learning.KohonenLearning
-
- setLearningRateChange(double) - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- setLearningRule(L) - Method in class org.neuroph.core.NeuralNetwork
-
Sets learning algorithm for this network
- setLeftHigh(double) - Method in class org.neuroph.core.transfer.Trapezoid
-
Sets left high point of trapezoid function
- setLeftLow(double) - Method in class org.neuroph.core.transfer.Trapezoid
-
Sets left low point of trapezoid function
- setMaxDelta(double) - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- setMaxError(double) - Method in class org.neuroph.core.learning.SupervisedLearning
-
Sets allowed network error, which indicates when to stopLearning training
- setMaxIterations(int) - Method in class org.neuroph.core.learning.IterativeLearning
-
Sets iteration limit for this learning algorithm
- setMaxIterations(int) - Method in class org.neuroph.nnet.comp.layer.CompetitiveLayer
-
Sets max iterations for neurons to compete in this layer
- setMaxLearningRate(double) - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- setMaxMomentum(double) - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- setMeanSquareError(double) - Method in class org.neuroph.eval.EvaluationResult
-
- setMinDelta(double) - Method in class org.neuroph.nnet.learning.ResilientPropagation
-
- setMinErrorChange(double) - Method in class org.neuroph.core.learning.SupervisedLearning
-
Sets min error change stopping criteria
- setMinErrorChangeIterationsLimit(int) - Method in class org.neuroph.core.learning.SupervisedLearning
-
Sets number of iterations for min error change stopping criteria
- setMinLearningRate(double) - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- setMinMomentum(double) - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- setMomentum(double) - Method in class org.neuroph.nnet.learning.MomentumBackpropagation
-
Sets the momentum factor
- setMomentumChange(double) - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- setName(String) - Method in class org.neuroph.util.benchmark.BenchmarkTask
-
Sets task name
- setNetworkType(NeuralNetworkType) - Method in class org.neuroph.core.NeuralNetwork
-
Sets type for this network
- setNeuralNetwork(NeuralNetwork) - Method in class org.neuroph.core.learning.LearningRule
-
Sets neural network for this learning rule
- setNeuralNetwork(NeuralNetwork) - Method in class org.neuroph.eval.EvaluationResult
-
- setNeuralNetwork(NeuralNetwork) - Method in class org.neuroph.nnet.learning.KohonenLearning
-
- setNeuron(int, Neuron) - Method in class org.neuroph.core.Layer
-
Sets (replace) the neuron at specified position in layer
- setNumberOfClusters(int) - Method in class org.neuroph.nnet.learning.kmeans.KMeansClustering
-
- setOutput(double) - Method in class org.neuroph.core.Neuron
-
Sets this neuron output
- setOutputLabels(String[]) - Method in class org.neuroph.core.NeuralNetwork
-
Sets labels for output neurons
- setOutputNeurons(List<Neuron>) - Method in class org.neuroph.core.NeuralNetwork
-
Sets output neurons
- setParentLayer(Layer) - Method in class org.neuroph.core.Neuron
-
Sets reference to parent layer for this neuron (layer in which the neuron
is located)
- setParentNetwork(NeuralNetwork) - Method in class org.neuroph.core.Layer
-
Sets reference on parent network
- setParentNetwork(NeuralNetwork) - Method in class org.neuroph.util.plugins.PluginBase
-
Sets the parent network for this plugin
- setProperty(String, Object) - Method in class org.neuroph.util.NeuronProperties
-
- setProperty(String, Object) - Method in class org.neuroph.util.Properties
-
- setRightHigh(double) - Method in class org.neuroph.core.transfer.Trapezoid
-
Sets right high point of trapezoid function
- setRightLow(double) - Method in class org.neuroph.core.transfer.Trapezoid
-
Sets right low point of trapezoid function
- setSampling(Sampling) - Method in class org.neuroph.eval.CrossValidationBak
-
- setSigma(double) - Method in class org.neuroph.core.transfer.Gaussian
-
Sets the sigma parametar for this function
- setSlope(double) - Method in class org.neuroph.core.transfer.Linear
-
Sets the slope parametar for this function
- setSlope(double) - Method in class org.neuroph.core.transfer.Sigmoid
-
Sets the slope parametar for this function
- setSlope(double) - Method in class org.neuroph.core.transfer.Tanh
-
Sets the slope parameter for this function
- setTestIterations(int) - Method in class org.neuroph.util.benchmark.BenchmarkTask
-
Sets number of test (benchmarking) iterations
- setThresh(double) - Method in class org.neuroph.nnet.comp.neuron.ThresholdNeuron
-
Sets threshold value for this neuron
- setThreshold(double) - Method in class org.neuroph.eval.ClassifierEvaluator
-
- setTrainingData(T) - Method in class org.neuroph.core.Weight
-
- setTrainingSet(DataSet) - Method in class org.neuroph.core.learning.LearningRule
-
Sets training set for this learning rule
- setTransferFunction(TransferFunction) - Method in class org.neuroph.core.Neuron
-
Sets transfer function
- setUseDynamicLearningRate(boolean) - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- setUseDynamicMomentum(boolean) - Method in class org.neuroph.nnet.learning.DynamicBackPropagation
-
- setValue(double) - Method in class org.neuroph.core.Weight
-
Sets the weight value
- setValueAt(int, double) - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
- setValues(int[][]) - Method in class org.neuroph.eval.classification.ConfusionMatrix
-
- setValues(double[]) - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
- setWarmupIterations(int) - Method in class org.neuroph.util.benchmark.BenchmarkTask
-
Sets the number of warmup iterations
- setWeight(Weight) - Method in class org.neuroph.core.Connection
-
Set the weight of the connection.
- setWeights(double[]) - Method in class org.neuroph.core.NeuralNetwork
-
Sets network weights from the specified double array
- setWeights(Weight[][]) - Method in class org.neuroph.nnet.comp.Kernel
-
- setWidth(int) - Method in class org.neuroph.nnet.comp.Dimension2D
-
- setWidth(int) - Method in class org.neuroph.nnet.comp.Kernel
-
Sets width of this kernel
- setXHigh(double) - Method in class org.neuroph.core.transfer.Ramp
-
Sets threshold for the high output level
- setXLow(double) - Method in class org.neuroph.core.transfer.Ramp
-
Sets threshold for the low output level
- setYHigh(double) - Method in class org.neuroph.core.transfer.Ramp
-
Sets output value for the high output level
- setYHigh(double) - Method in class org.neuroph.core.transfer.Step
-
Set output value for the high output level
- setYLow(double) - Method in class org.neuroph.core.transfer.Ramp
-
Sets output value for the low output level
- setYLow(double) - Method in class org.neuroph.core.transfer.Step
-
Set output value for the low output level
- Sgn - Class in org.neuroph.core.transfer
-
Sgn neuron transfer function.
- Sgn() - Constructor for class org.neuroph.core.transfer.Sgn
-
- shouldFlattenNetworks() - Method in class org.neuroph.util.Neuroph
-
Get setting for flatten network (from Encog engine)
- shuffle() - Method in class org.neuroph.core.data.DataSet
-
- shutdown() - Method in class org.neuroph.util.Neuroph
-
Shuts down the Encog engine
- Sigmoid - Class in org.neuroph.core.transfer
-
Sigmoid neuron transfer function.
- Sigmoid() - Constructor for class org.neuroph.core.transfer.Sigmoid
-
Creates an instance of Sigmoid neuron transfer function with default
slope=1.
- Sigmoid(double) - Constructor for class org.neuroph.core.transfer.Sigmoid
-
Creates an instance of Sigmoid neuron transfer function with specified
value for slope parametar.
- Sigmoid(Properties) - Constructor for class org.neuroph.core.transfer.Sigmoid
-
Creates an instance of Sigmoid neuron transfer function with the
specified properties.
- SigmoidDeltaRule - Class in org.neuroph.nnet.learning
-
Delta rule learning algorithm for perceptrons with sigmoid (or any other diferentiable continuous) functions.
- SigmoidDeltaRule() - Constructor for class org.neuroph.nnet.learning.SigmoidDeltaRule
-
Creates new SigmoidDeltaRule
- SimulatedAnnealingLearning - Class in org.neuroph.nnet.learning
-
This class implements a simulated annealing learning rule for supervised
neural networks.
- SimulatedAnnealingLearning(NeuralNetwork, double, double, int) - Constructor for class org.neuroph.nnet.learning.SimulatedAnnealingLearning
-
Construct a simulated annleaing trainer for a feedforward neural network.
- SimulatedAnnealingLearning(NeuralNetwork) - Constructor for class org.neuroph.nnet.learning.SimulatedAnnealingLearning
-
- Sin - Class in org.neuroph.core.transfer
-
Sin neuron transfer function.
- Sin() - Constructor for class org.neuroph.core.transfer.Sin
-
- size() - Method in class org.neuroph.core.data.DataSet
-
Returns number of training elements in this training set set
- size() - Method in class org.neuroph.nnet.learning.kmeans.Cluster
-
Returns number of vectors assigned to this cluster.
- size() - Method in class org.neuroph.nnet.learning.kmeans.KVector
-
- SmallErrorChangeStop - Class in org.neuroph.core.learning.stop
-
Stops learning rule if error change has been too small for specified number
of iterations
- SmallErrorChangeStop(SupervisedLearning) - Constructor for class org.neuroph.core.learning.stop.SmallErrorChangeStop
-
- split(int) - Method in class org.neuroph.core.data.DataSet
-
Splits data set into specified number of parts and returns them as a list.
- split(double...) - Method in class org.neuroph.core.data.DataSet
-
Splits data sets into parts of specified sizes.
- split(int, Random) - Method in class org.neuroph.core.data.DataSet
-
- split(Random, double...) - Method in class org.neuroph.core.data.DataSet
-
- start() - Method in class org.neuroph.util.benchmark.Stopwatch
-
Starts measuring time
- Stats() - Constructor for class org.neuroph.eval.classification.ClassificationMetrics.Stats
-
- STD_DEV - Static variable in class org.neuroph.util.DataSetStatistics
-
- Step - Class in org.neuroph.core.transfer
-
Step neuron transfer function.
- Step() - Constructor for class org.neuroph.core.transfer.Step
-
Creates an instance of Step transfer function
- Step(Properties) - Constructor for class org.neuroph.core.transfer.Step
-
Creates an instance of Step transfer function with specified properties
- stop() - Method in class org.neuroph.util.benchmark.Stopwatch
-
Stops measuring time
- StopCondition - Interface in org.neuroph.core.learning.stop
-
Interface for learning rule stop condition.
- stopConditions - Variable in class org.neuroph.core.learning.IterativeLearning
-
- stopLearning() - Method in class org.neuroph.core.learning.LearningRule
-
Stops learning
- stopLearning() - Method in class org.neuroph.core.NeuralNetwork
-
Stops learning
- Stopwatch - Class in org.neuroph.util.benchmark
-
A class to help benchmark code, it simulates a real stop watch.
- Stopwatch() - Constructor for class org.neuroph.util.benchmark.Stopwatch
-
- SubSampling - Class in org.neuroph.util.data.sample
-
This class provides sub-sampling of a data set, and creates a specified number of subsets form given data set.
- SubSampling(int) - Constructor for class org.neuroph.util.data.sample.SubSampling
-
Sampling will produce a specified number of subsets of equal sizes.
- SubSampling(double...) - Constructor for class org.neuroph.util.data.sample.SubSampling
-
Sampling will create subsets of specified sizes.
- Sum - Class in org.neuroph.core.input
-
Performs summing of all input vector elements.
- Sum() - Constructor for class org.neuroph.core.input.Sum
-
- SUM - Static variable in class org.neuroph.util.DataSetStatistics
-
- sumConfusionMatrix(List<ConfusionMatrix>, DataSet) - Method in class org.neuroph.eval.KFoldCrossValidation
-
- SumSqr - Class in org.neuroph.core.input
-
Calculates squared sum of all input vector elements.
- SumSqr() - Constructor for class org.neuroph.core.input.SumSqr
-
- SupervisedHebbianLearning - Class in org.neuroph.nnet.learning
-
Supervised hebbian learning rule.
- SupervisedHebbianLearning() - Constructor for class org.neuroph.nnet.learning.SupervisedHebbianLearning
-
Creates new instance of SupervisedHebbianLearning algorithm
- SupervisedHebbianNetwork - Class in org.neuroph.nnet
-
Hebbian neural network with supervised Hebbian learning algorithm.
- SupervisedHebbianNetwork(int, int) - Constructor for class org.neuroph.nnet.SupervisedHebbianNetwork
-
Creates an instance of Supervised Hebbian Network net with specified
number neurons in input and output layer
- SupervisedHebbianNetwork(int, int, TransferFunctionType) - Constructor for class org.neuroph.nnet.SupervisedHebbianNetwork
-
Creates an instance of Supervised Hebbian Network with specified number
of neurons in input layer and output layer, and transfer function
- SupervisedLearning - Class in org.neuroph.core.learning
-
Base class for all supervised learning algorithms.
- SupervisedLearning() - Constructor for class org.neuroph.core.learning.SupervisedLearning
-
Creates new supervised learning rule
- UnsupervisedHebbianLearning - Class in org.neuroph.nnet.learning
-
Unsupervised hebbian learning rule.
- UnsupervisedHebbianLearning() - Constructor for class org.neuroph.nnet.learning.UnsupervisedHebbianLearning
-
Creates new instance of UnsupervisedHebbianLearning algorithm
- UnsupervisedHebbianNetwork - Class in org.neuroph.nnet
-
Hebbian neural network with unsupervised Hebbian learning algorithm.
- UnsupervisedHebbianNetwork(int, int) - Constructor for class org.neuroph.nnet.UnsupervisedHebbianNetwork
-
Creates an instance of Unsuervised Hebian net with specified number
of neurons in input and output layer
- UnsupervisedHebbianNetwork(int, int, TransferFunctionType) - Constructor for class org.neuroph.nnet.UnsupervisedHebbianNetwork
-
Creates an instance of Unsuervised Hebian net with specified number
of neurons in input layer and output layer, and transfer function
- UnsupervisedLearning - Class in org.neuroph.core.learning
-
Base class for all unsupervised learning algorithms.
- UnsupervisedLearning() - Constructor for class org.neuroph.core.learning.UnsupervisedLearning
-
Creates new unsupervised learning rule
- updateNetworkWeights() - Method in class org.neuroph.core.learning.UnsupervisedLearning
-
This method implements the weight adjustment
- updateNetworkWeights() - Method in class org.neuroph.nnet.learning.CompetitiveLearning
-
Adjusts weights for the winning neuron
- updateNetworkWeights() - Method in class org.neuroph.nnet.learning.UnsupervisedHebbianLearning
-
Adjusts weights for the output neurons
- updateNeuronWeights(Neuron) - Method in class org.neuroph.nnet.learning.AntiHebbianLearning
-
This method implements weights update procedure for the single neuron
- updateNeuronWeights(Neuron) - Method in class org.neuroph.nnet.learning.BinaryHebbianLearning
-
This method implements weights update procedure for the single neuron
- updateNeuronWeights(Neuron) - Method in class org.neuroph.nnet.learning.GeneralizedHebbianLearning
-
This method implements weights update procedure for the single neuron
- updateNeuronWeights(Neuron) - Method in class org.neuroph.nnet.learning.InstarLearning
-
This method implements weights update procedure for the single neuron
- updateNeuronWeights(Neuron) - Method in class org.neuroph.nnet.learning.OjaLearning
-
This method implements weights update procedure for the single neuron
- updateNeuronWeights(Neuron) - Method in class org.neuroph.nnet.learning.OutstarLearning
-
This method implements weights update procedure for the single neuron
- updateNeuronWeights(Neuron, double) - Method in class org.neuroph.nnet.learning.SupervisedHebbianLearning
-
This method implements weights update procedure for the single neuron
- updateNeuronWeights(Neuron) - Method in class org.neuroph.nnet.learning.UnsupervisedHebbianLearning
-
This method implements weights update procedure for the single neuron
- URLInputAdapter - Class in org.neuroph.util.io
-
Implementation of InputAdapter interface for reading neural network inputs from URL.
- URLInputAdapter(URL) - Constructor for class org.neuroph.util.io.URLInputAdapter
-
Creates a new URLInputAdapter by opening a connection to URL specified by the input param
- URLInputAdapter(String) - Constructor for class org.neuroph.util.io.URLInputAdapter
-
Creates a new URLInputAdapter by opening a connection to URL specified by the input param
- URLOutputAdapter - Class in org.neuroph.util.io
-
Implementation of OutputAdapter interface for writing neural network outputs to URL.
- URLOutputAdapter(URL) - Constructor for class org.neuroph.util.io.URLOutputAdapter
-
Creates a new URLOutputAdapter by opening a connection to URL specified by the url input param
- URLOutputAdapter(String) - Constructor for class org.neuroph.util.io.URLOutputAdapter
-
Creates a new URLOutputAdapter by opening a connection to URL specified by the string url input param
- Utils - Class in org.neuroph.eval.classification
-