超级最小的XOR神经网络无法学习..我做错了什么

自学神经网络的基础知识，我决定在学习XOR函数的超级网络上进行破解。它由两个输入神经元，两个隐藏的神经元和一个输出神经元组成。问题是它没有学到。该代码超级最小，应使用任何C 11支持编译器进行编译。

#include <stdio.h>
#include <stdlib.h>
#include <vector>
#include <cmath>
#include <algorithm>
#include <numeric>
using namespace std;
float tanh_activate(float x) { return (exp(2*x)-1)/(exp(2*x)+1); }
float tanh_gradient(float x) { return 1-x*x; }
vector<float> input = { 0.0f, 0.0f };
vector<float> hiddenW = { 0.5f, 0.5f };
vector<float> hidden = { 0.0f, 0.0f };
vector<float> output = { 0.0f };
void forward()
{
    float inputSum = accumulate( input.begin(), input.end(), 0.0f );
    hidden[0] = tanh_activate( inputSum ) * hiddenW[0];
    hidden[1] = tanh_activate( inputSum ) * hiddenW[1];
    output[0] = tanh_activate( accumulate( hidden.begin(), hidden.end(), 0.0f ) );
}
void backward( float answer )
{
    auto outputError = answer - output[0];
    auto error = outputError * tanh_gradient( output[0] );
    auto layerError = accumulate( hiddenW.begin(),
                                  hiddenW.end(),
                                  0.0f,
                                  [error]( float sum, float w ) {
                                      return sum + (w * error);
                                  } );
    // Calculating error for each activation in hidden layer but this is unused
    // currently since their is only one hidden layer.
    vector<float> layerE( hidden.size() );
    transform( hidden.begin(),
               hidden.end(),
               layerE.begin(),
               [layerError]( float a ) {
                   return tanh_gradient( a ) * layerError;
               } );
    // update weights
    for( auto wi = hiddenW.begin(), ai = hidden.begin(); wi != hiddenW.end(); ++wi, ++ai )
        *wi += *ai * error;
}
int main( int argc, char* argv[] )
{
    for( int i = 0; i < 10000000; ++i )
    {
        // pick two bits at random...
        int i1 = ((random() % 2)==0)?1.0f:0.0f;
        int i2 = ((random() % 2)==0)?1.0f:0.0f;
        // load our input layer...
        input[0] = (float)i1;
        input[1] = (float)i2;
        // compute network output...
        forward();
        // we're teaching our network XOR
        float expected = ((i1^i2)==0) ? 0.0f : 1.0f;
        if( i % 10000 == 0 )
        {
            printf("output = %fn",output[0]);
            printf("expected = %fn",expected);
        }
        // backprop...
        backward( expected );
    }
    return 0;
}