Uses of Interface
org.apache.commons.math3.ml.neuralnet.FeatureInitializer
Packages that use FeatureInitializer
Package
Description
Neural networks.
One-dimensional neural networks.
Two-dimensional neural networks.
-
Uses of FeatureInitializer in org.apache.commons.math3.ml.neuralnet
Methods in org.apache.commons.math3.ml.neuralnet that return FeatureInitializerModifier and TypeMethodDescriptionstatic FeatureInitializerFeatureInitializerFactory.function(UnivariateFunction f, double init, double inc) Creates an initializer from a univariate functionf(x).static FeatureInitializerFeatureInitializerFactory.randomize(RealDistribution random, FeatureInitializer orig) Adds some amount of random data to the given initializer.static FeatureInitializerFeatureInitializerFactory.uniform(double min, double max) Uniform sampling of the given range.static FeatureInitializerFeatureInitializerFactory.uniform(RandomGenerator rng, double min, double max) Uniform sampling of the given range.Methods in org.apache.commons.math3.ml.neuralnet with parameters of type FeatureInitializerModifier and TypeMethodDescriptionstatic FeatureInitializerFeatureInitializerFactory.randomize(RealDistribution random, FeatureInitializer orig) Adds some amount of random data to the given initializer. -
Uses of FeatureInitializer in org.apache.commons.math3.ml.neuralnet.oned
Constructors in org.apache.commons.math3.ml.neuralnet.oned with parameters of type FeatureInitializerModifierConstructorDescriptionNeuronString(int num, boolean wrap, FeatureInitializer[] featureInit) Creates a one-dimensional network: Each neuron not located on the border of the mesh has two neurons linked to it. -
Uses of FeatureInitializer in org.apache.commons.math3.ml.neuralnet.twod
Constructors in org.apache.commons.math3.ml.neuralnet.twod with parameters of type FeatureInitializerModifierConstructorDescriptionNeuronSquareMesh2D(int numRows, boolean wrapRowDim, int numCols, boolean wrapColDim, SquareNeighbourhood neighbourhoodType, FeatureInitializer[] featureInit) Creates a two-dimensional network composed of square cells: Each neuron not located on the border of the mesh has four neurons linked to it.