Name | Description | Type | Package | Framework |
Adaline | Adaline neural network architecture with LMS learning rule. | Class | org.neuroph.nnet | Neuroph |
|
And | Performs logic AND operation on input vector. | Class | org.neuroph.core.input | Neuroph |
|
AntiHebbianLearning | A variant of Hebbian learning called Anti-Hebbian learning. | Class | org.neuroph.nnet.learning | Neuroph |
|
AutoencoderNetwork | | Class | org.neuroph.nnet | Neuroph |
|
BackPropagation | Back Propagation learning rule for Multi Layer Perceptron neural networks. | Class | org.neuroph.nnet.learning | Neuroph |
|
BAM | Bidirectional Associative MemoryAuthor:Zoran Sevarac See Also:Serialized Form | Class | org.neuroph.nnet | Neuroph |
|
Benchmark | This class is main benchmark driver. | Class | org.neuroph.util.benchmark | Neuroph |
|
BenchmarkSample | This is an example how to use Neuroph microbenchmarking frameworkAuthor:Zoran Sevarac | Class | org.neuroph.util.benchmark | Neuroph |
|
BenchmarkTask | This class is an abstract base class for specific microbenchmarking tasksAuthor:Zoran Sevarac | Class | org.neuroph.util.benchmark | Neuroph |
|
BenchmarkTaskResults | This class holds benchmarking results, elapsed times for all iterations and various statistics min, max, avg times and standard deviation | Class | org.neuroph.util.benchmark | Neuroph |
|
BiasNeuron | Neuron with constant high output (1), used as biasAuthor:Zoran Sevarac See Also:Neuron, | Class | org.neuroph.nnet.comp.neuron | Neuroph |
|
BinaryDeltaRule | Delta rule learning algorithm for perceptrons with step functions. | Class | org.neuroph.nnet.learning | Neuroph |
|
BinaryHebbianLearning | Hebbian-like learning algorithm used for Hopfield network. | Class | org.neuroph.nnet.learning | Neuroph |
|
BufferedDataSet | This class can be used for large training sets, which are partialy read from file during the training. | Class | org.neuroph.core.data | Neuroph |
|
Cluster | This class represents a single cluster, with corresponding centroid and assigned vectorsAuthor:Zoran Sevarac | Class | org.neuroph.nnet.learning.kmeans | Neuroph |
|
CompetitiveLayer | Represents layer of competitive neurons, and provides methods for competition. | Class | org.neuroph.nnet.comp.layer | Neuroph |
|
CompetitiveLearning | Competitive learning rule. | Class | org.neuroph.nnet.learning | Neuroph |
|
CompetitiveNetwork | Two layer neural network with competitive learning rule. | Class | org.neuroph.nnet | Neuroph |
|
CompetitiveNeuron | Provides neuron behaviour specific for competitive neurons which are used in competitive layers, and networks with competitive learning. | Class | org.neuroph.nnet.comp.neuron | Neuroph |
|
Connection | Weighted connection to another neuron. | Class | org.neuroph.core | Neuroph |
|
ConnectionFactory | Provides methods to connect neurons by creating Connection objects. | Class | org.neuroph.util | Neuroph |
|
ConvolutionalBackpropagation | | Class | org.neuroph.nnet.learning | Neuroph |
|
ConvolutionalLayer | Convolutional layer is a special type of layer, used in convolutional neural networks. | Class | org.neuroph.nnet.comp.layer | Neuroph |
|
ConvolutionalNetwork | Convolutional neural network with backpropagation algorithm modified for convolutional networks. | Class | org.neuroph.nnet | Neuroph |
|
ConvolutionalUtils | Utility functions for convolutional networksAuthor:Boris Fulurija, Zorn Sevarac | Class | org.neuroph.nnet.comp | Neuroph |
|
DataSet | This class represents a collection of data rows (DataSetRow instances) used for training and testing neural network. | Class | org.neuroph.core.data | Neuroph |
|
DataSetRow | This class represents single data row in a data set. | Class | org.neuroph.core.data | Neuroph |
|
DecimalScaleNormalizer | Decimal scaling normalization method, which normalize data by moving decimal point in regard to max element in training set (by columns) Normalization is | Class | org.neuroph.util.data.norm | Neuroph |
|
DelayedConnection | Represents the connection between neurons which can delay signal. | Class | org.neuroph.nnet.comp | Neuroph |
|
DelayedNeuron | Provides behaviour for neurons with delayed output. | Class | org.neuroph.nnet.comp.neuron | Neuroph |
|
Difference | Performs the vector difference operation on input andAuthor:Zoran Sevarac See Also:Serialized Form | Class | org.neuroph.core.input | Neuroph |
|
DistortRandomizer | This class provides distort randomization technique, which distorts existing weight values using specified distortion factor. | Class | org.neuroph.util.random | Neuroph |
|
DynamicBackPropagation | Backpropagation learning rule with dynamic learning rate and momentumAuthor:Zoran Sevarac See Also:Serialized Form | Class | org.neuroph.nnet.learning | Neuroph |
|
ElmanNetwork | Under development: Learning rule BackProp Through Time requiredAuthor:zoranSee Also:Serialized Form | Class | org.neuroph.nnet | Neuroph |
|
ErrorFunction | Interface for calculating total network error during the learning. | Interface | org.neuroph.core.learning.error | Neuroph |
|
FeatureMapsLayer | 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, | Class | org.neuroph.nnet.comp.layer | Neuroph |
|
FileInputAdapter | | Class | org.neuroph.util.io | Neuroph |
|
FileOutputAdapter | | Class | org.neuroph.util.io | Neuroph |
|
FileUtils | Utility methods for working with files. | Class | org.neuroph.util | Neuroph |
|
Gaussian | Gaussian neuron transfer function. | Class | org.neuroph.core.transfer | Neuroph |
|
GaussianRandomizer | This class provides Gaussian randomization technique using Box Muller method. | Class | org.neuroph.util.random | Neuroph |
|
GeneralizedHebbianLearning | A variant of Hebbian learning called Generalized Hebbian learning. | Class | org.neuroph.nnet.learning | Neuroph |
|
Hopfield | Hopfield neural network. | Class | org.neuroph.nnet | Neuroph |
|
HopfieldLearning | Learning algorithm for the Hopfield neural network. | Class | org.neuroph.nnet.learning | Neuroph |
|
InputAdapter | Interface for reading neural network inputs from various data sources. | Interface | org.neuroph.util.io | Neuroph |
|
InputFunction | Neuron's input function. | Class | org.neuroph.core.input | Neuroph |
|
InputLayer | Represents a layer of input neurons - a typical neural network input layerAuthor:Zoran Sevarac See Also:InputNeuron, | Class | org.neuroph.nnet.comp.layer | Neuroph |
|
InputMapsLayer | Input layer for convolutional networksAuthor:Boris Fulurija, Zoran SevaracSee Also:Serialized Form | Class | org.neuroph.nnet.comp.layer | Neuroph |
|
InputNeuron | Provides input neuron behaviour - neuron with input extranaly set, which just transfer that input to output without change. | Class | org.neuroph.nnet.comp.neuron | Neuroph |
|
InputOutputNeuron | Provides behaviour specific for neurons which act as input and the output neurons within the same layer. | Class | org.neuroph.nnet.comp.neuron | Neuroph |
|
InputStreamAdapter | | Class | org.neuroph.util.io | Neuroph |
|
Instar | Instar neural network with Instar learning rule. | Class | org.neuroph.nnet | Neuroph |
|
InstarLearning | Hebbian-like learning rule for Instar network. | Class | org.neuroph.nnet.learning | Neuroph |
|
IOHelper | This class is helper for feeding neural network with data using some InputAdapter and writing network output using OutputAdapter | Class | org.neuroph.util.io | Neuroph |
|
IterativeLearning | Base class for all iterative learning algorithms. | Class | org.neuroph.core.learning | Neuroph |
|
JDBCInputAdapter | | Class | org.neuroph.util.io | Neuroph |
|
JDBCOutputAdapter | | Class | org.neuroph.util.io | Neuroph |
|
JordanNetwork | Under development: Learning rule BackProp Through Time requiredAuthor:zoranSee Also:Serialized Form | Class | org.neuroph.nnet | Neuroph |
|
Kernel | Kernel used in convolution networks. | Class | org.neuroph.nnet.comp | Neuroph |
|
KMeansClustering | 1. | Class | org.neuroph.nnet.learning.kmeans | Neuroph |
|
KNearestNeighbour | calculate distances to all vectors from list and find minimum vector | Class | org.neuroph.nnet.learning.knn | Neuroph |
|
Kohonen | Kohonen neural network. | Class | org.neuroph.nnet | Neuroph |
|
KohonenLearning | Learning algorithm for Kohonen network. | Class | org.neuroph.nnet.learning | Neuroph |
|
KVector | Represents feature vector used in k-means clustering algorithmAuthor:Zoran Sevarac, Uros Stojkic | Class | org.neuroph.nnet.learning.kmeans | Neuroph |
|
Layer | Layer of neurons in a neural network. | Class | org.neuroph.core | Neuroph |
|
Layer2D | 2D Layer provides 2D layout of the neurons in layer. | Class | org.neuroph.nnet.comp.layer | Neuroph |
|
LayerFactory | Provides methods to create instance of a Layer with specifed number of neurons and neuron's properties. | Class | org.neuroph.util | Neuroph |
|
LearningEvent | This class holds information about the source of some learning event. | Class | org.neuroph.core.events | Neuroph |
|
LearningEventListener | This interface is implemented by classes who are listening to learning events (iterations, error etc. | Interface | org.neuroph.core.events | Neuroph |
|
LearningEventType | enum LearningEventTypeAuthor:Zoran Sevarac | Class | org.neuroph.core.events | Neuroph |
|
LearningRule | Base class for all neural network learning algorithms. | Class | org.neuroph.core.learning | Neuroph |
|
Linear | Linear neuron transfer function. | Class | org.neuroph.core.transfer | Neuroph |
|
LMS | LMS learning rule for neural networks. | Class | org.neuroph.nnet.learning | Neuroph |
|
Log | Log neuron transfer function. | Class | org.neuroph.core.transfer | Neuroph |
|
Max | Performs max function on input vectorAuthor:Zoran Sevarac See Also:Serialized Form | Class | org.neuroph.core.input | Neuroph |
|
MaxErrorStop | Stops learning rule if total network error is below some specified valueAuthor:Zoran Sevarac See Also:Serialized Form | Class | org.neuroph.core.learning.stop | Neuroph |
|
MaxIterationsStop | Stops learning rule if specified number of iterations has been reachedAuthor:Zoran Sevarac See Also:Serialized Form | Class | org.neuroph.core.learning.stop | Neuroph |
|
MaxMinNormalizer | MaxMin normalization method, which normalize data in regard to min and max elements in training set (by columns) Normalization is done according to formula: | Class | org.neuroph.util.data.norm | Neuroph |
|
MaxNet | Max Net neural network with competitive learning rule. | Class | org.neuroph.nnet | Neuroph |
|
MaxNormalizer | Max normalization method, which normalize data in regard to max element in training set (by columns) Normalization is done according to formula: | Class | org.neuroph.util.data.norm | Neuroph |
|
MeanSquaredError | Commonly used mean squared errorAuthor:Zoran Sevarac See Also:Serialized Form | Class | org.neuroph.core.learning.error | Neuroph |
|
Min | Performs min function on input vectorAuthor:Zoran Sevarac See Also:Serialized Form | Class | org.neuroph.core.input | Neuroph |
|
MomentumBackpropagation | Backpropagation learning rule with momentum. | Class | org.neuroph.nnet.learning | Neuroph |
|
MultiLayerPerceptron | Multi Layer Perceptron neural network with Back propagation learning algorithm. | Class | org.neuroph.nnet | Neuroph |
|
MyBenchmarkTask | This class is example of custom benchmarking task for Multi Layer Perceptorn network Note that this benchmark only measures the speed at implementation level - the | Class | org.neuroph.util.benchmark | Neuroph |
|
NeuralNetwork | Base class for artificial neural networks. | Class | org.neuroph.core | Neuroph |
|
NeuralNetworkCODEC | A CODEC encodes and decodes neural networks, much like the more standard definition of a CODEC encodes and decodes audio/video. | Class | org.neuroph.util | Neuroph |
|
NeuralNetworkEvent | This class holds information about the source and type of some neural network event. | Class | org.neuroph.core.events | Neuroph |
|
NeuralNetworkEventListener | This interface is implemented by classes who are listening to neural network events events (to be defined) NeuralNetworkEvent class holds the information about event. | Interface | org.neuroph.core.events | Neuroph |
|
NeuralNetworkEventType | enum NeuralNetworkEventTypeAuthor:Zoran Sevarac | Class | org.neuroph.core.events | Neuroph |
|
NeuralNetworkFactory | Provides methods to create various neural networks. | Class | org.neuroph.util | Neuroph |
|
NeuralNetworkType | enum NeuralNetworkTypeContains neural network types and labels. | Class | org.neuroph.util | Neuroph |
|
NeuroFuzzyPerceptron | The NeuroFuzzyReasoner class represents Neuro Fuzzy Reasoner architecture. | Class | org.neuroph.nnet | Neuroph |
|
Neuron | Basic general neuron model according to McCulloch-Pitts neuron model. | Class | org.neuroph.core | Neuroph |
|
NeuronFactory | Provides methods to create customized instances of Neurons. | Class | org.neuroph.util | Neuroph |
|
NeuronProperties | Represents properties of a neuron. | Class | org.neuroph.util | Neuroph |
|
Neuroph | | Class | org.neuroph.util | Neuroph |
|
NeurophArrayList | Resizable-array implementation of the List interface. | Class | org.neuroph.util | Neuroph |
|
NeurophException | Base exception type for Neuroph. | Class | org.neuroph.core.exceptions | Neuroph |
|
NeurophInputException | This exception is thrown when error occurs when reading input using some InputAdapterAuthor:Zoran Sevarac See Also:InputAdapter, | Class | org.neuroph.util.io | Neuroph |
|
NeurophOutputException | This exception is thrown when some error occurs when writing neural network output using some output adapter. | Class | org.neuroph.util.io | Neuroph |
|
NguyenWidrowRandomizer | This class provides NguyenWidrow randmization technique, which gives very good results for Multi Layer Perceptrons trained with back propagation family of learning rules. | Class | org.neuroph.util.random | Neuroph |
|
Normalizer | Interface for data set normalization methods. | Interface | org.neuroph.util.data.norm | Neuroph |
|
OjaLearning | Oja learning rule wich is a modification of unsupervised hebbian learning. | Class | org.neuroph.nnet.learning | Neuroph |
|
Or | Performs logic OR operation on input vector. | Class | org.neuroph.core.input | Neuroph |
|
OutputAdapter | Interface for writing neural network outputs to some destination. | Interface | org.neuroph.util.io | Neuroph |
|
OutputStreamAdapter | | Class | org.neuroph.util.io | Neuroph |
|
Outstar | Outstar neural network with Outstar learning rule. | Class | org.neuroph.nnet | Neuroph |
|
OutstarLearning | Hebbian-like learning rule for Outstar network. | Class | org.neuroph.nnet.learning | Neuroph |
|
Perceptron | Perceptron neural network with some LMS based learning algorithm. | Class | org.neuroph.nnet | Neuroph |
|
PerceptronLearning | Perceptron learning rule for perceptron neural networks. | Class | org.neuroph.nnet.learning | Neuroph |
|
PluginBase | Base class for all neural network plugins. | Class | org.neuroph.util.plugins | Neuroph |
|
PoolingLayer | Pooling layer is a special type of feature maps layer (FeatureMapsLayer) which is used in convolutional networks. | Class | org.neuroph.nnet.comp.layer | Neuroph |
|
Product | Performs multiplication of all input vector elements. | Class | org.neuroph.core.input | Neuroph |
|
Properties | Represents a general set of properties for neuroph objectsAuthor:Zoran Sevarac See Also:Serialized Form | Class | org.neuroph.util | Neuroph |
|
Ramp | Ramp neuron transfer function. | Class | org.neuroph.core.transfer | Neuroph |
|
RangeNormalizer | This class does normalization of a data set to specified rangeAuthor:Zoran Sevarac | Class | org.neuroph.util.data.norm | Neuroph |
|
RangeRandomizer | This class provides ranged weights randomizer, which randomize weights in specified [min, max] range. | Class | org.neuroph.util.random | Neuroph |
|
RBFLearning | Learning rule for Radial Basis Function networks. | Class | org.neuroph.nnet.learning | Neuroph |
|
RBFNetwork | Radial basis function neural network. | Class | org.neuroph.nnet | Neuroph |
|
ResilientPropagation | Resilient Propagation learning rule used for Multi Layer Perceptron neural networks. | Class | org.neuroph.nnet.learning | Neuroph |
|
Sampling | Interface for data set sampling methods. | Interface | org.neuroph.util.data.sample | Neuroph |
|
Sgn | Sgn neuron transfer function. | Class | org.neuroph.core.transfer | Neuroph |
|
Sigmoid | Sigmoid neuron transfer function. | Class | org.neuroph.core.transfer | Neuroph |
|
SigmoidDeltaRule | Delta rule learning algorithm for perceptrons with sigmoid (or any other diferentiable continuous) functions. | Class | org.neuroph.nnet.learning | Neuroph |
|
SimulatedAnnealingLearning | This class implements a simulated annealing learning rule for supervised neural networks. | Class | org.neuroph.nnet.learning | Neuroph |
|
Sin | Sin neuron transfer function. | Class | org.neuroph.core.transfer | Neuroph |
|
SmallErrorChangeStop | Stops learning rule if error change has been too small for specified numberAuthor:Zoran Sevarac See Also:Serialized Form | Class | org.neuroph.core.learning.stop | Neuroph |
|
Step | Step neuron transfer function. | Class | org.neuroph.core.transfer | Neuroph |
|
StopCondition | Interface for learning rule stop condition. | Interface | org.neuroph.core.learning.stop | Neuroph |
|
Stopwatch | A class to help benchmark code, it simulates a real stop watch. | Class | org.neuroph.util.benchmark | Neuroph |
|
SubSampling | This class provides subsampling of a data set, and creates two subsets of a given data set - for training and testing. | Class | org.neuroph.util.data.sample | Neuroph |
|
Sum | Performs summing of all input vector elements. | Class | org.neuroph.core.input | Neuroph |
|
SumSqr | Calculates squared sum of all input vector elements. | Class | org.neuroph.core.input | Neuroph |
|
SupervisedHebbianLearning | Supervised hebbian learning rule. | Class | org.neuroph.nnet.learning | Neuroph |
|
SupervisedHebbianNetwork | Hebbian neural network with supervised Hebbian learning algorithm. | Class | org.neuroph.nnet | Neuroph |
|
SupervisedLearning | Base class for all supervised learning algorithms. | Class | org.neuroph.core.learning | Neuroph |
|
Tanh | Tanh neuron transfer function. | Class | org.neuroph.core.transfer | Neuroph |
|
ThresholdNeuron | Provides behaviour for neurons with threshold. | Class | org.neuroph.nnet.comp.neuron | Neuroph |
|
TrainingSetImport | Handles training set importsAuthor:Zoran Sevarac, Ivan Nedeljkovic, Kokanovic Rados | Class | org.neuroph.util | Neuroph |
|
TransferFunction | Abstract base class for all neuron tranfer functions. | Class | org.neuroph.core.transfer | Neuroph |
|
TransferFunctionType | enum TransferFunctionTypeContains transfer functions types and labels. | Class | org.neuroph.util | Neuroph |
|
Trapezoid | Fuzzy trapezoid neuron tranfer function. | Class | org.neuroph.core.transfer | Neuroph |
|
UnsupervisedHebbianLearning | Unsupervised hebbian learning rule. | Class | org.neuroph.nnet.learning | Neuroph |
|
UnsupervisedHebbianNetwork | Hebbian neural network with unsupervised Hebbian learning algorithm. | Class | org.neuroph.nnet | Neuroph |
|
UnsupervisedLearning | Base class for all unsupervised learning algorithms. | Class | org.neuroph.core.learning | Neuroph |
|
URLInputAdapter | | Class | org.neuroph.util.io | Neuroph |
|
URLOutputAdapter | | Class | org.neuroph.util.io | Neuroph |
|
VectorParser | Provides methods to parse strings as Integer or Double vectors. | Class | org.neuroph.util | Neuroph |
|
VectorSizeMismatchException | Thrown to indicate that vector size does not match the network input or training element size. | Class | org.neuroph.core.exceptions | Neuroph |
|
Weight | Neuron connection weight. | Class | org.neuroph.core | Neuroph |
|
WeightedSum | Optimized version of weighted input functionAuthor:Zoran SevaracSee Also:Serialized Form | Class | org.neuroph.core.input | Neuroph |
|
WeightsRandomizer | Basic weights randomizer, iterates and randomizes all connection weights in network. | Class | org.neuroph.util.random | Neuroph |