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));
}
/**
* Set the input to the neural network.
*
* @param input The input.
*/
private void setInput(final BiPolarNeuralData input) {
double activation;
for (int i = 0; i < this.layerF1.getNeuronCount(); i++) {
activation =
(input.getBoolean(i) ? 1 : 0)
/ (1 + this.a1 * ((input.getBoolean(i) ? 1 : 0) + this.b1) + this.c1);
this.outputF1.setData(i, (activation > 0));
}
}
/**
* Compute the output from the F1 layer.
*
* @param input The input to the F1 layer.
*/
private void computeF1(final BiPolarNeuralData input) {
double sum, activation;
for (int i = 0; i < this.layerF1.getNeuronCount(); i++) {
sum =
this.synapseF1toF2.getMatrix().get(i, this.winner)
* (this.outputF2.getBoolean(this.winner) ? 1 : 0);
activation =
((input.getBoolean(i) ? 1 : 0) + this.d1 * sum - this.b1)
/ (1 + this.a1 * ((input.getBoolean(i) ? 1 : 0) + this.d1 * sum) + this.c1);
this.outputF1.setData(i, activation > 0);
}
}
String displayTour(BiPolarNeuralData data) {
StringBuilder result = new StringBuilder();
int n1, n2;
boolean first;
for (n1 = 0; n1 < NUM_CITIES; n1++) {
first = true;
result.append("[");
for (n2 = 0; n2 < NUM_CITIES; n2++) {
if (data.getBoolean(n1 * NUM_CITIES + n2)) {
if (first) {
first = false;
result.append(n2);
} else {
result.append(", " + n2);
}
}
}
result.append("]");
if (n1 != NUM_CITIES - 1) {
result.append(" -> ");
}
}
return result.toString();
}
public double lengthOfTour(BiPolarNeuralData data) {
double result;
int n1, n2, n3;
result = 0;
for (n1 = 0; n1 < NUM_CITIES; n1++) {
for (n2 = 0; n2 < NUM_CITIES; n2++) {
if (data.getBoolean(((n1) % NUM_CITIES) * NUM_CITIES + n2)) break;
}
for (n3 = 0; n3 < NUM_CITIES; n3++) {
if (data.getBoolean(((n1 + 1) % NUM_CITIES) * NUM_CITIES + n3)) break;
}
result += distance[n2][n3];
}
return result;
}
/**
* Get the magnitude of the specified input.
*
* @param input The input to calculate the magnitude for.
* @return The magnitude of the specified pattern.
*/
public double magnitude(final BiPolarNeuralData input) {
double result;
result = 0;
for (int i = 0; i < this.layerF1.getNeuronCount(); i++) {
result += input.getBoolean(i) ? 1 : 0;
}
return result;
}
public boolean isValidTour(BiPolarNeuralData data) {
int cities, stops;
for (int n1 = 0; n1 < NUM_CITIES; n1++) {
cities = 0;
stops = 0;
for (int n2 = 0; n2 < NUM_CITIES; n2++) {
if (data.getBoolean(n1 * NUM_CITIES + n2)) {
if (++cities > 1) return false;
}
if (data.getBoolean(n2 * NUM_CITIES + n1)) {
if (++stops > 1) return false;
}
}
if ((cities != 1) || (stops != 1)) return false;
}
return true;
}
/**
* Copy the output from the network to another object.
*
* @param output The target object for the output from the network.
*/
private void getOutput(final BiPolarNeuralData output) {
for (int i = 0; i < this.layerF2.getNeuronCount(); i++) {
output.setData(i, this.outputF2.getBoolean(i));
}
}
