我正在构建一个测试神经网络，它肯定不起作用。我的主要问题是反向传播。根据我的研究，我知道使用 sigmoid 函数很容易。因此，我通过 (1-Output)(Output)(target-Output) 更新每个权重，但问题是如果我的输出为 1 但我的目标不是？如果它在某个时候是 1，那么权重更新将始终为 0...现在我只是想让该死的东西添加来自 2 个输入神经元的输入，因此最佳权重应该只是 1 作为输出神经元只需添加其输入。我确定我在很多地方都搞砸了，但这是我的代码：
public class Main {
public static void main(String[] args) {
Double[] inputs = {1.0, 2.0};
ArrayList<Double> answers = new ArrayList<Double>();
answers.add(3.0);
net myNeuralNet = new net(2, 1, answers);
for(int i=0; i<200; i++){
myNeuralNet.setInputs(inputs);
myNeuralNet.start();
myNeuralNet.backpropagation();
myNeuralNet.printOutput();
System.out.println("*****");
for(int j=0; j<myNeuralNet.getOutputs().size(); j++){
myNeuralNet.getOutputs().get(j).resetInput();
myNeuralNet.getOutputs().get(j).resetOutput();
myNeuralNet.getOutputs().get(j).resetNumCalled();
}
}
}
}
package myneuralnet;
import java.util.ArrayList;
public class net {
private ArrayList<neuron> inputLayer;
private ArrayList<neuron> outputLayer;
private ArrayList<Double> answers;
public net(Integer numInput, Integer numOut, ArrayList<Double> answers){
inputLayer = new ArrayList<neuron>();
outputLayer = new ArrayList<neuron>();
this.answers = answers;
for(int i=0; i<numOut; i++){
outputLayer.add(new neuron(true));
}
for(int i=0; i<numInput; i++){
ArrayList<Double> randomWeights = createRandomWeights(numInput);
inputLayer.add(new neuron(outputLayer, randomWeights, -100.00, true));
}
for(int i=0; i<numOut; i++){
outputLayer.get(i).setBackConn(inputLayer);
}
}
public ArrayList<neuron> getOutputs(){
return outputLayer;
}
public void backpropagation(){
for(int i=0; i<answers.size(); i++){
neuron iOut = outputLayer.get(i);
ArrayList<neuron> iOutBack = iOut.getBackConn();
Double iSigDeriv = (1-iOut.getOutput())*iOut.getOutput();
Double iError = (answers.get(i) - iOut.getOutput());
System.out.println("Answer: "+answers.get(i) + " iOut: "+iOut.getOutput()+" Error: "+iError+" Sigmoid: "+iSigDeriv);
for(int j=0; j<iOutBack.size(); j++){
neuron jNeuron = iOutBack.get(j);
Double ijWeight = jNeuron.getWeight(i);
System.out.println("ijWeight: "+ijWeight);
System.out.println("jNeuronOut: "+jNeuron.getOutput());
jNeuron.setWeight(i, ijWeight+(iSigDeriv*iError*jNeuron.getOutput()));
}
}
for(int i=0; i<inputLayer.size(); i++){
inputLayer.get(i).resetInput();
inputLayer.get(i).resetOutput();
}
}
public ArrayList<Double> createRandomWeights(Integer size){
ArrayList<Double> iWeight = new ArrayList<Double>();
for(int i=0; i<size; i++){
Double randNum = (2*Math.random())-1;
iWeight.add(randNum);
}
return iWeight;
}
public void setInputs(Double[] is){
for(int i=0; i<is.length; i++){
inputLayer.get(i).setInput(is[i]);
}
for(int i=0; i<outputLayer.size(); i++){
outputLayer.get(i).resetInput();
}
}
public void start(){
for(int i=0; i<inputLayer.size(); i++){
inputLayer.get(i).fire();
}
}
public void printOutput(){
for(int i=0; i<outputLayer.size(); i++){
System.out.println(outputLayer.get(i).getOutput().toString());
}
}
}
package myneuralnet;
import java.util.ArrayList;
public class neuron {
private ArrayList<neuron> connections;
private ArrayList<neuron> backconns;
private ArrayList<Double> weights;
private Double threshold;
private Double input;
private Boolean isOutput = false;
private Boolean isInput = false;
private Double totalSignal;
private Integer numCalled;
private Double myOutput;
public neuron(ArrayList<neuron> conns, ArrayList<Double> weights, Double threshold){
this.connections = conns;
this.weights = weights;
this.threshold = threshold;
this.totalSignal = 0.00;
this.numCalled = 0;
this.backconns = new ArrayList<neuron>();
this.input = 0.00;
}
public neuron(ArrayList<neuron> conns, ArrayList<Double> weights, Double threshold, Boolean isin){
this.connections = conns;
this.weights = weights;
this.threshold = threshold;
this.totalSignal = 0.00;
this.numCalled = 0;
this.backconns = new ArrayList<neuron>();
this.input = 0.00;
this.isInput = isin;
}
public neuron(Boolean tf){
this.connections = new ArrayList<neuron>();
this.weights = new ArrayList<Double>();
this.threshold = 0.00;
this.totalSignal = 0.00;
this.numCalled = 0;
this.isOutput = tf;
this.backconns = new ArrayList<neuron>();
this.input = 0.00;
}
public void setInput(Double input){
this.input = input;
}
public void setOut(Boolean tf){
this.isOutput = tf;
}
public void resetNumCalled(){
numCalled = 0;
}
public void setBackConn(ArrayList<neuron> backs){
this.backconns = backs;
}
public Double getOutput(){
return myOutput;
}
public Double getInput(){
return totalSignal;
}
public Double getRealInput(){
return input;
}
public ArrayList<Double> getWeights(){
return weights;
}
public ArrayList<neuron> getBackConn(){
return backconns;
}
public Double getWeight(Integer i){
return weights.get(i);
}
public void setWeight(Integer i, Double d){
weights.set(i, d);
}
public void setOutput(Double d){
myOutput = d;
}
public void activation(Double myInput){
numCalled++;
totalSignal += myInput;
if(numCalled==backconns.size() && isOutput){
System.out.println("Total Sig: "+totalSignal);
setInput(totalSignal);
setOutput(totalSignal);
}
}
public void activation(){
Double activationValue = 1 / (1 + Math.exp(input));
setInput(activationValue);
fire();
}
public void fire(){
for(int i=0; i<connections.size(); i++){
Double iWeight = weights.get(i);
neuron iConn = connections.get(i);
myOutput = (1/(1+(Math.exp(-input))))*iWeight;
iConn.activation(myOutput);
}
}
public void resetInput(){
input = 0.00;
totalSignal = 0.00;
}
public void resetOutput(){
myOutput = 0.00;
}
}
好的，这是很多代码，所以请允许我解释一下。网络现在很简单，只有一个输入层和一个输出层 --- 我想稍后添加一个隐藏层，但我现在正在采取婴儿步骤。每一层都是神经元的数组列表。输入神经元加载了输入，在这个例子中是一个 1 和一个 2。这些神经元触发，计算输入的 sigmoid 并将其输出到输出神经元，输出神经元将它们相加并存储值。然后网络通过获取 (answer-output) (output) (1-output)(特定输入神经元的输出) 进行反向传播，并相应地更新权重。很多时候，它循环通过，我得到无穷大，这似乎与负权重或 sigmoid 相关。如果没有发生这种情况，它会收敛到 1，并且由于 (1-output of 1) 为 0，我的权重停止更新。
numCalled 和 totalSignal 值只是让算法在继续之前等待所有神经元输入。我知道我这样做是一种奇怪的方式，但是神经元类有一个称为连接的神经元数组列表来保存它正向连接的神经元。另一个名为 backconns 的数组列表保存反向连接。我也应该更新正确的权重，因为我得到了神经元 i 和 j 之间的所有反向连接，但是在所有神经元 j（i 上面的层）中，我只拉权重 i。我为混乱道歉 --- 我已经尝试了好几个小时，但仍然无法弄清楚。任何帮助是极大的赞赏！