name: NeuralNetwork


g++ [flags ...] file ... -l /isip/tools/lib/$ISIP_BINARY/lib_pr.a

#include <NeuralNetwork.h>

boolean setEpochs(long arg);
long getEpochs();
boolean setLearningRate(float arg);
float getLearningRate();
boolean setMomentum(float arg);
float getMomentum();
boolean setBias(float arg);
float getBias();
boolean init(long epochs, long units, long layers = DEF_HIDDEN_LAYERS, float bias = DEF_BIAS, float rate = DEF_ETA, float momentum = DEF_MOMENTUM);
boolean loadFeatures(String& arg);
boolean loadOutputs(String& arg);
boolean loadTestFeatures(String& arg);
boolean loadTestOutputs(String& arg);
boolean train(String& train, String& output, String& model);
boolean test(String& model, String& test, String& output);
boolean writeModel(String& arg);
quick start:



A class that implements a massively distributed processor made up of simple processing units, which has a natural propensity for storing experiential knowladge and making it available for use.


[1] Elaine, Rich and Knight, "Artificial Intelligence", Second Edition, McGraw Hill, New York, 1991.

[2] S. Haykin, "Neural Networks", Second Edition, Prentice Hall, New Jersey, 1999.


public constants:

error codes:

protected data:

required public methods:

class-specific public methods:

private data: