public void testFeedforwardPersist() throws Throwable {
NeuralDataSet trainingData = new BasicNeuralDataSet(XOR.XOR_INPUT, XOR.XOR_IDEAL);
BasicNetwork network = createNetwork();
Train train = new Backpropagation(network, trainingData, 0.7, 0.9);
for (int i = 0; i < 5000; i++) {
train.iteration();
network = (BasicNetwork) train.getNetwork();
}
TestCase.assertTrue("Error too high for backpropagation", train.getError() < 0.1);
TestCase.assertTrue("XOR outputs not correct", XOR.verifyXOR(network, 0.1));
EncogPersistedCollection encog = new EncogPersistedCollection();
encog.add(network);
encog.save("encogtest.xml");
EncogPersistedCollection encog2 = new EncogPersistedCollection();
encog2.load("encogtest.xml");
new File("encogtest.xml").delete();
BasicNetwork n = (BasicNetwork) encog2.getList().get(0);
TestCase.assertTrue("Error too high for load", n.calculateError(trainingData) < 0.1);
}
public void testHopfieldPersist() throws Exception {
boolean input[] = {true, false, true, false};
BasicNetwork network = new BasicNetwork();
network.addLayer(new HopfieldLayer(4));
NeuralData data = new BiPolarNeuralData(input);
Train train = new TrainHopfield(data, network);
train.iteration();
EncogPersistedCollection encog = new EncogPersistedCollection();
encog.add(network);
encog.save("encogtest.xml");
EncogPersistedCollection encog2 = new EncogPersistedCollection();
encog2.load("encogtest.xml");
new File("encogtest.xml").delete();
BasicNetwork network2 = (BasicNetwork) encog2.getList().get(0);
BiPolarNeuralData output = (BiPolarNeuralData) network2.compute(new BiPolarNeuralData(input));
TestCase.assertTrue(output.getBoolean(0));
TestCase.assertFalse(output.getBoolean(1));
TestCase.assertTrue(output.getBoolean(2));
TestCase.assertFalse(output.getBoolean(3));
}
/**
* * <br>
* Updates the neural networks</br> <br>
* Assumes that the *
*/
private void trainNeuralNets(int id) {
Train train =
new ResilientPropagation(array_of_neural_nets[id], input_datas[id].getTrainingSet());
int epoch = 0;
while (train.getError() > error_allowed && epoch < max_epoch) {
train.iteration();
epoch++;
}
}
private BasicNetwork trainNetwork(
BasicNetwork network,
NeuralDataSet trainingSet,
double learningRate,
double momentum,
double maxError,
int maxIteration) {
final Train train = new Backpropagation(network, trainingSet, learningRate, momentum);
int epoch = 1;
do {
train.iteration();
epoch++;
} while ((epoch < maxIteration) && (train.getError() > maxError));
return (BasicNetwork) train.getNetwork();
}