$\sqrt{公式}$
$$\left[ \begin{array}{a} a^l_1 \\ ⋮ \\ a^l_{d_l} \end{array}\right] = \sigma( \left[ \begin{matrix} w^l_{1,1} & ⋯ & w^l_{1,d_{l-1}} \\ ⋮ & ⋱ & ⋮ \\ w^l_{d_l,1} & ⋯ & w^l_{d_l,d_{l-1}} \\ \end{matrix}\right] · \left[ \begin{array}{x} a^{l-1}_1 \\ ⋮ \\ ⋮ \\ a^{l-1}_{d_{l-1}} \end{array}\right] + \left[ \begin{array}{b} b^l_1 \\ ⋮ \\ b^l_{d_l} \end{array}\right]) $$
$$\mathbb{E}(X) = \int x d F(x) = \left\{ \begin{aligned} \sum_x x f(x) \; & \text{ if } X \text{ is discrete} \\ \int x f(x) dx \; & \text{ if } X \text{ is continuous } \end{aligned} \right. $$
Inline math $\frac{1}{2}$.
哈哈
这篇文章的内容已被作者标记为“过时”/“需要更新”/“不具参考意义”。