我试图教2个输入,4个隐藏节点(全部在同一层)和1个输出节点的神经网络。二进制表示可以正常工作,但是我对双极性有问题。我无法弄清楚为什么,但总误差有时会汇集到2.xx左右的相同数字。我的sigmoid是2 /(1 + exp(-x)) - 1.也许我在sigmoiding在错误的地方。例如,为了计算输出误差,我应该比较sigmoided输出与期望值还是sigmoided期望值?神经网络教学:双极XOR
我在这里关注这个网站:http://galaxy.agh.edu.pl/~vlsi/AI/backp_t_en/backprop.html,但他们使用不同的功能,然后我被指示使用。即使当我尝试实现他们的功能时,我仍遇到同样的问题。无论哪种方式,我停留在相同数量的一半时间(不同的实现不同的数字)。请告诉我,如果我的代码在某个地方犯了错误,或者这是正常的(我不明白这是怎么回事)。动量被设置为0.这是一个常见的0动量问题吗?我们应该使用错误的功能是:
如果UI是一个输出单元
Error(i) = (Ci - ui) * f'(Si)
如果用户界面是一个隐藏的单元
Error(i) = Error(Output) * weight(i to output) * f'(Si)
public double sigmoid(double x) {
double fBipolar, fBinary, temp;
temp = (1 + Math.exp(-x));
fBipolar = (2/temp) - 1;
fBinary = 1/temp;
if(bipolar){
return fBipolar;
}else{
return fBinary;
}
}
// Initialize the weights to random values.
private void initializeWeights(double neg, double pos) {
for(int i = 0; i < numInputs + 1; i++){
for(int j = 0; j < numHiddenNeurons; j++){
inputWeights[i][j] = Math.random() - pos;
if(inputWeights[i][j] < neg || inputWeights[i][j] > pos){
print("ERROR ");
print(inputWeights[i][j]);
}
}
}
for(int i = 0; i < numHiddenNeurons + 1; i++){
hiddenWeights[i] = Math.random() - pos;
if(hiddenWeights[i] < neg || hiddenWeights[i] > pos){
print("ERROR ");
print(hiddenWeights[i]);
}
}
}
// Computes output of the NN without training. I.e. a forward pass
public double outputFor (double[] argInputVector) {
for(int i = 0; i < numInputs; i++){
inputs[i] = argInputVector[i];
}
double weightedSum = 0;
for(int i = 0; i < numHiddenNeurons; i++){
weightedSum = 0;
for(int j = 0; j < numInputs + 1; j++){
weightedSum += inputWeights[j][i] * inputs[j];
}
hiddenActivation[i] = sigmoid(weightedSum);
}
weightedSum = 0;
for(int j = 0; j < numHiddenNeurons + 1; j++){
weightedSum += (hiddenActivation[j] * hiddenWeights[j]);
}
return sigmoid(weightedSum);
}
//Computes the derivative of f
public static double fPrime(double u){
double fBipolar, fBinary;
fBipolar = 0.5 * (1 - Math.pow(u,2));
fBinary = u * (1 - u);
if(bipolar){
return fBipolar;
}else{
return fBinary;
}
}
// This method is used to update the weights of the neural net.
public double train (double [] argInputVector, double argTargetOutput){
double output = outputFor(argInputVector);
double lastDelta;
double outputError = (argTargetOutput - output) * fPrime(output);
if(outputError != 0){
for(int i = 0; i < numHiddenNeurons + 1; i++){
hiddenError[i] = hiddenWeights[i] * outputError * fPrime(hiddenActivation[i]);
deltaHiddenWeights[i] = learningRate * outputError * hiddenActivation[i] + (momentum * lastDelta);
hiddenWeights[i] += deltaHiddenWeights[i];
}
for(int in = 0; in < numInputs + 1; in++){
for(int hid = 0; hid < numHiddenNeurons; hid++){
lastDelta = deltaInputWeights[in][hid];
deltaInputWeights[in][hid] = learningRate * hiddenError[hid] * inputs[in] + (momentum * lastDelta);
inputWeights[in][hid] += deltaInputWeights[in][hid];
}
}
}
return 0.5 * (argTargetOutput - output) * (argTargetOutput - output);
}