小编Bre*_*ent的帖子

我知道Java Double.NaN是什么.我有一些产生的Java代码NaN.

// calculate errors
delta = m1 + m2 - M;
eta = f1 + f2 - F;
for (int i = 0; i < numChildren; i++) {
  epsilon[i] = p[i]*m1+(1-p[i])*m2+q[i]*f1+(1-q[i])*f2-C[i];
}

// use errors in gradient descent
// set aside differences for the p's and q's
float mDiff = m1 - m2;
float fDiff = f1 - f2;
// first update m's and f's
m1 -= rate*delta;
m2 -= rate*delta;
f1 -= rate*eta;
f2 -= …