反向传导算法
From Ufldl
(Created page with "反向传导算法") |
|||
Line 1: | Line 1: | ||
- | + | :【原文】: | |
+ | Suppose we have a fixed training set <math>\{ (x^{(1)}, y^{(1)}), \ldots, (x^{(m)}, y^{(m)}) \}</math> of <math>m</math> training examples. We can train our neural network using batch gradient descent. In detail, for a single training example <math>(x,y)</math>, we define the cost function with respect to that single example to be: | ||
+ | |||
+ | :【初译】: | ||
+ | 假设我们有一个固定的训练集<math>\{ (x^{(1)}, y^{(1)}), \ldots, (x^{(m)}, y^{(m)}) \}</math>,它包含<math>m</math>个训练样本。我们可以用批量梯度下降法训练我们的神经网络。下面进行详细介绍。针对单独的训练样本<math>(x,y)</math>,我们定义关于它的代价函数为: | ||
+ | :【一校】: | ||
+ | |||
+ | :<math> | ||
+ | \begin{align} | ||
+ | J(W,b; x,y) = \frac{1}{2} \left\| h_{W,b}(x) - y \right\|^2. | ||
+ | \end{align} | ||
+ | </math> | ||
+ | |||
+ | :【原文】: | ||
+ | :【初译】: | ||
+ | :【一校】: |