0

我有以下代码

public void alearningrate(){

        //adopt learningrate 
        System.out.println(errorpositive+""+learningrate);
        if ((errorpositive&&errorgradient>0)||!errorpositive&&errorgradient<0){
            learningrate=learningrate*1.5;

        }else{
            learningrate=learningrate*0.75;
        }
        if (learningrate<0.0001){
            learningrate=0.0001;
        }
    }

    public void lastblame(double blame){

        errorpositive=errorgradient>0;
        errorgradient= Math.exp(-value)/Math.pow(1+Math.exp(-value), 2)*blame;
        if (value==Double.NaN){
            System.out.println("nan detected=?");
            errorgradient=1;
        }
        for (int i=0; i<weight.length;i++){
            weight[i]=weight[i]+learningrate*source[i].output()*errorgradient;
        }

        //alearningrate();

    }
    public void hiddenblame(double blame){
        System.out.println(value);
        errorpositive=errorgradient>0;
        errorgradient=Math.exp(-value)/Math.pow(1+Math.exp(-value), 2)*blame;
        if (value==Double.NaN){
            System.out.println("nan detected=?");
            errorgradient=1;
        }
        for (int i=0; i<weight.length;i++){
            weight[i]=weight[i]+learningrate*source[i].output()*errorgradient;
        }
        System.out.println(errorgradient);
        alearningrate();

    }

但是，这会导致错误梯度迅速变为 NaN，但如果我决定删除 alearningrate()，则代码运行良好。我查看了我的函数 errorgradient 函数，它永远不会产生 nan，有人知道我为什么一直得到 NaN 吗？

4

0 回答 0