求指导,我用你的代码运行一个不一样的东西,结果很失望
import java.util.Random;
public class BpDeep{
public double[][] layer;//神经网络各层节点
public double[][] layerErr;//神经网络各节点误差
public double[][][] layer_weight;//各层节点权重
public double[][][] layer_weight_delta;//各层节点权重动量
public double mobp;//动量系数
public double rate;//学习系数
public BpDeep(int[] layernum, double rate, double mobp){
this.mobp = mobp;
this.rate = rate;
layer = new double[layernum.length][];
layerErr = new double[layernum.length][];
layer_weight = new double[layernum.length][][];
layer_weight_delta = new double[layernum.length][][];
Random random = new Random();
for(int l=0;l<layernum.length;l++){
layer[l]=new double[layernum[l]];
layerErr[l]=new double[layernum[l]];
if(l+1<layernum.length){
layer_weight[l]=new double[layernum[l]+1][layernum[l+1]];
layer_weight_delta[l]=new double[layernum[l]+1][layernum[l+1]];
for(int j=0;j<layernum[l]+1;j++)
for(int i=0;i<layernum[l+1];i++)
layer_weight[l][j][i]=random.nextDouble();//随机初始化权重
}
}
}
//逐层向前计算输出
public double[] computeOut(double[] in){
for(int l=1;l<layer.length;l++){
for(int j=0;j<layer[l].length;j++){
double z=layer_weight[l-1][layer[l-1].length][j];
for(int i=0;i<layer[l-1].length;i++){
layer[l-1][i]=l==1?in[i]:layer[l-1][i];
z+=layer_weight[l-1][i][j]*layer[l-1][i];
}
layer[l][j]=1/(1+Math.exp(-z));
}
}
return layer[layer.length-1];
}
//逐层反向计算误差并修改权重
public void updateWeight(double[] tar){
int l=layer.length-1;
for(int j=0;j<layerErr[l].length;j++)
layerErr[l][j]=layer[l][j]*(1-layer[l][j])*(tar[j]-layer[l][j]);
while(l-->0){
for(int j=0;j<layerErr[l].length;j++){
double z = 0.0;
for(int i=0;i<layerErr[l+1].length;i++){
z=z+l>0?layerErr[l+1][i]*layer_weight[l][j][i]:0;
layer_weight_delta[l][j][i]= mobp*layer_weight_delta[l][j][i]+rate*layerErr[l+1][i]*layer[l][j];//隐含层动量调整
layer_weight[l][j][i]+=layer_weight_delta[l][j][i];//隐含层权重调整
if(j==layerErr[l].length-1){
layer_weight_delta[l][j+1][i]= mobp*layer_weight_delta[l][j+1][i]+rate*layerErr[l+1][i];//截距动量调整
layer_weight[l][j+1][i]+=layer_weight_delta[l][j+1][i];//截距权重调整
}
}
layerErr[l][j]=z*layer[l][j]*(1-layer[l][j]);//记录误差
}
}
}
public void train(double[] in, double[] tar){
double[] out = computeOut(in);
updateWeight(tar);
}
}
import java.util.Arrays;
public class MyBPtest1{
public static void main(String[] args){
//初始化神经网络的基本配置
//第一个参数是一个整型数组,表示神经网络的层数和每层节点数,比如{3,10,10,10,10,2}表示输入层是3个节点,输出层是2个节点,中间有4层隐含层,每层10个节点
/////////第二个参数是学习步长(过小会使收敛速度太慢;过大则会使预测不准,跳过一些细节),
/////////第三个参数是动量系数(使波动小的预测重新振荡起来)
BpDeep bp = new BpDeep(new int[]{5,5,1}, 0.15, 0.9);
////////对于输入样本如果只有一个数。没关系,大不了{,}第二项里的data和target全为0,,,,!!!!这理解是错误
////////因为我们设定了输入层为2,才会有两个输入({,},{,}}这样的东西;同理输入层也为如此
////////所以说如果是5个输入,一个输出对于data就{{,,,,},{,,,,}。。。。。。};;;;;对于target{,,,,}
double[][] data = new double[][]{{192,195,194,193,193},
{195,194,193,193,195},{194,193,193,195,201},
{193,193,195,201,205},{193,195,201,205,205},
{195,201,205,205,203},{201,205,205,203,203},
{205,205,203,203,202},{205,203,203,202,206},
{203,203,202,206,204},{203,202,206,204,204},
{202,206,204,204,203},{206,204,204,203,199},
{204,204,203,199,195},{204,203,199,195,182},
{203,199,195,182,179},{199,195,182,179,178},
{195,182,179,178,176},{182,179,178,176,175},
{179,178,176,175,173},{178,176,175,173,175},
{176,175,173,175,182},{175,173,175,182,183},
{173,175,182,183,185},{175,182,183,185,179}};
//设置目标数据,对应4个坐标数据的分类
double[][] target = new double[][]{{195},{201},{205},{205},{203},
{203},{202},{206},{204},{204},{203},{199},{195},{182},{179},
{178},{176},{175},{173},{175},{182},{183},{185},{179},{182}};
//迭代训练5000次
///////这里我们没有设置训练到了某一精确度自动停止,而是实打实的训练这些次数
for(int n=0;n<5000;n++)
for(int i=0;i<data.length;i++)
bp.train(data[i], target[i]);
//根据训练结果来检验样本数据
for(int j=0;j<data.length;j++){
double[] result = bp.computeOut(data[j]);
System.out.println(Arrays.toString(data[j])+":"+Arrays.toString(result));
}
//根据训练结果来预测一条新数据的分类
double[] x = new double[]{192,195,194,193,193};
double[] result = bp.computeOut(x);
System.out.println(Arrays.toString(x)+":"+Arrays.toString(result));
}
} |