Neuroph

org.neuroph.nnet
Class MultiLayerPerceptron

java.lang.Object
  extended by java.util.Observable
      extended by org.neuroph.core.NeuralNetwork
          extended by org.neuroph.nnet.MultiLayerPerceptron
All Implemented Interfaces:
java.io.Serializable, java.lang.Runnable

public class MultiLayerPerceptron
extends NeuralNetwork

The MultiLayerPerceptron class that represents Multi Layer Perceptron neural network with Back propagation learning algorithm.

See Also:
Serialized Form

Field Summary
private static long serialVersionUID
          The class fingerprint that is set to indicate serialization compatibility with a previous version of the class.
 
Constructor Summary
MultiLayerPerceptron(int... neuronsInLayers)
           
MultiLayerPerceptron(java.util.Vector<java.lang.Integer> neuronsInLayers)
          Creates new MultiLayerPerceptron with specified number neurons in getLayersIterator
MultiLayerPerceptron(java.util.Vector<java.lang.Integer> neuronsInLayers, NeuronProperties neuronProperties)
          Creates new MultiLayerPerceptron net with specified number neurons in getLayersIterator
MultiLayerPerceptron(java.util.Vector<java.lang.Integer> neuronsInLayers, TransferFunctionType transferFunctionType)
           
 
Method Summary
private  void createNetwork(java.util.Vector<java.lang.Integer> neuronsInLayers, NeuronProperties neuronProperties)
          Creates MultiLayerPerceptron Network architecture - fully connected feedforward with specified number of neurons in each layer
 
Methods inherited from class org.neuroph.core.NeuralNetwork
addLayer, addLayer, addPlugin, calculate, createConnection, getInputNeurons, getLayerAt, getLayers, getLayersCount, getLayersIterator, getLearningRule, getNetworkType, getOutput, getOutputNeurons, getPlugin, indexOf, learn, load, notifyChange, randomizeWeights, removeLayer, removeLayerAt, removePlugin, reset, run, save, setInput, setInputNeurons, setLearningRule, setNetworkType, setOutputNeurons, stopLearning, toString
 
Methods inherited from class java.util.Observable
addObserver, clearChanged, countObservers, deleteObserver, deleteObservers, hasChanged, notifyObservers, notifyObservers, setChanged
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Field Detail

serialVersionUID

private static final long serialVersionUID
The class fingerprint that is set to indicate serialization compatibility with a previous version of the class.

See Also:
Constant Field Values
Constructor Detail

MultiLayerPerceptron

public MultiLayerPerceptron(java.util.Vector<java.lang.Integer> neuronsInLayers)
Creates new MultiLayerPerceptron with specified number neurons in getLayersIterator

Parameters:
neuronsInLayers - collection of neuron number in getLayersIterator

MultiLayerPerceptron

public MultiLayerPerceptron(int... neuronsInLayers)

MultiLayerPerceptron

public MultiLayerPerceptron(java.util.Vector<java.lang.Integer> neuronsInLayers,
                            TransferFunctionType transferFunctionType)

MultiLayerPerceptron

public MultiLayerPerceptron(java.util.Vector<java.lang.Integer> neuronsInLayers,
                            NeuronProperties neuronProperties)
Creates new MultiLayerPerceptron net with specified number neurons in getLayersIterator

Parameters:
neuronNumInLayers - collection of neuron numbers in getLayersIterator
neuronProperties - neuron propreties
Method Detail

createNetwork

private void createNetwork(java.util.Vector<java.lang.Integer> neuronsInLayers,
                           NeuronProperties neuronProperties)
Creates MultiLayerPerceptron Network architecture - fully connected feedforward with specified number of neurons in each layer

Parameters:
neuronsInLayers - collection of neuron numbers in getLayersIterator
neuronProperties - neuron propreties

Neuroph