org.encog.neural.pattern
Interface NeuralNetworkPattern

All Known Implementing Classes:
ADALINEPattern, ART1Pattern, BAMPattern, BoltzmannPattern, CPNPattern, ElmanPattern, FeedForwardPattern, HopfieldPattern, JordanPattern, PNNPattern, RadialBasisPattern, SOMPattern, SVMPattern

public interface NeuralNetworkPattern

Patterns are used to create common sorts of neural networks. Information about the structure of the neural network is communicated to the pattern, and then generate is called to produce a neural network of this type.

Author:
jheaton

Method Summary
 void addHiddenLayer(int count)
          Add the specified hidden layer.
 void clear()
          Clear the hidden layers so that they can be redefined.
 MLMethod generate()
          Generate the specified neural network.
 void setActivationFunction(ActivationFunction activation)
          Set the activation function to be used for all created layers that allow an activation function to be specified.
 void setInputNeurons(int count)
          Set the number of input neurons.
 void setOutputNeurons(int count)
          Set the number of output neurons.
 

Method Detail

addHiddenLayer

void addHiddenLayer(int count)
Add the specified hidden layer.

Parameters:
count - The number of neurons in the hidden layer.

clear

void clear()
Clear the hidden layers so that they can be redefined.


generate

MLMethod generate()
Generate the specified neural network.

Returns:
The resulting neural network.

setActivationFunction

void setActivationFunction(ActivationFunction activation)
Set the activation function to be used for all created layers that allow an activation function to be specified. Not all patterns allow the activation function to be specified.

Parameters:
activation - The activation function.

setInputNeurons

void setInputNeurons(int count)
Set the number of input neurons.

Parameters:
count - The number of input neurons.

setOutputNeurons

void setOutputNeurons(int count)
Set the number of output neurons.

Parameters:
count - The output neuron count.


Copyright © 2014. All Rights Reserved.