org.neuroph.nnet

Class ConvolutionalNetwork

java.lang.Object

org.neuroph.core.NeuralNetwork<ConvolutionalBackpropagation>

org.neuroph.nnet.ConvolutionalNetwork

All Implemented Interfaces:

Serializable

public class ConvolutionalNetwork
extends NeuralNetwork<ConvolutionalBackpropagation>

Convolutional neural network with backpropagation algorithm modified for convolutional networks.

TODO: provide Hiton, LeCun, AndrewNg implementation specific features

Author:

Boris Fulurija, Zoran Sevarac

See Also:

ConvolutionalBackpropagation, Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ConvolutionalNetwork.Builder

Field Summary

Fields inherited from class org.neuroph.core.NeuralNetwork

outputBuffer

Constructor Summary

Constructors

Constructor and Description
ConvolutionalNetwork()

Method Summary

Modifier and Type	Method and Description
void	setInput(double... inputVector) Sets network input, to all feature maps in input layer

Methods inherited from class org.neuroph.core.NeuralNetwork

addLayer, addLayer, addListener, addPlugin, calculate, createConnection, createFromFile, createFromFile, fireNetworkEvent, getInputNeurons, getInputsCount, getLabel, getLayerAt, getLayers, getLayersCount, getLearningRule, getNetworkType, getOutput, getOutputLabels, getOutputNeurons, getOutputsCount, getPlugin, getWeights, indexOf, isEmpty, learn, learn, load, load, pauseLearning, randomizeWeights, randomizeWeights, randomizeWeights, randomizeWeights, removeLayer, removeLayerAt, removeListener, removePlugin, reset, resumeLearning, save, setInputNeurons, setLabel, setLearningRule, setNetworkType, setOutputLabels, setOutputNeurons, setWeights, stopLearning, toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

ConvolutionalNetwork

public ConvolutionalNetwork()

Method Detail

setInput

public void setInput(double... inputVector)
              throws VectorSizeMismatchException

Sets network input, to all feature maps in input layer

Overrides:

setInput in class NeuralNetwork<ConvolutionalBackpropagation>

Parameters:

inputVector -

Throws:

VectorSizeMismatchException