エラーを逆伝播して重みを調整するメソッドを含むオンラインの例を見つけました。これが正確にどのように機能し、どの重み更新アルゴリズムが使用されているのか疑問に思っていました。勾配降下でしょうか?
/**
* all output propagate back
*
* @param expectedOutput
* first calculate the partial derivative of the error with
* respect to each of the weight leading into the output neurons
* bias is also updated here
*/
public void applyBackpropagation(double expectedOutput[]) {
// error check, normalize value ]0;1[
for (int i = 0; i < expectedOutput.length; i++) {
double d = expectedOutput[i];
if (d < 0 || d > 1) {
if (d < 0)
expectedOutput[i] = 0 + epsilon;
else
expectedOutput[i] = 1 - epsilon;
}
}
int i = 0;
for (Neuron n : outputLayer) {
ArrayList<Connection> connections = n.getAllInConnections();
for (Connection con : connections) {
double ak = n.getOutput();
double ai = con.leftNeuron.getOutput();
double desiredOutput = expectedOutput[i];
double partialDerivative = -ak * (1 - ak) * ai
* (desiredOutput - ak);
double deltaWeight = -learningRate * partialDerivative;
double newWeight = con.getWeight() + deltaWeight;
con.setDeltaWeight(deltaWeight);
con.setWeight(newWeight + momentum * con.getPrevDeltaWeight());
}
i++;
}
// update weights for the hidden layer
for (Neuron n : hiddenLayer) {
ArrayList<Connection> connections = n.getAllInConnections();
for (Connection con : connections) {
double aj = n.getOutput();
double ai = con.leftNeuron.getOutput();
double sumKoutputs = 0;
int j = 0;
for (Neuron out_neu : outputLayer) {
double wjk = out_neu.getConnection(n.id).getWeight();
double desiredOutput = (double) expectedOutput[j];
double ak = out_neu.getOutput();
j++;
sumKoutputs = sumKoutputs
+ (-(desiredOutput - ak) * ak * (1 - ak) * wjk);
}
double partialDerivative = aj * (1 - aj) * ai * sumKoutputs;
double deltaWeight = -learningRate * partialDerivative;
double newWeight = con.getWeight() + deltaWeight;
con.setDeltaWeight(deltaWeight);
con.setWeight(newWeight + momentum * con.getPrevDeltaWeight());
}
}
}