Machine Learning Fundamentals · 免费预览

隐藏层与激活函数

单个仿射映射无法表达作用方向会发生反转的关系，而在仿射映射之间插入非线性函数进行复合，即可消除这一限制。

1. What linearity assumes

What linearity assumes

2. A hidden layer

A hidden layer

3. Two standard activations

Two standard activations

4. Why a hidden layer needs a nonlinearity

An MLP layer computes $\mathbf{H} = \sigma(\mathbf{X}\mathbf{W}^{(1)} + \mathbf{b}^{(1)})$ and a second layer computes $\mathbf{O} = \mathbf{H}\mathbf{W}^{(2)} + \mathbf{b}^{(2)}$ . The activation $\sigma$ is replaced by the identity, so $\mathbf{H} = \mathbf{X}\mathbf{W}^{(1)} + \mathbf{b}^{(1)}$ . What is the effect on the model?

5. The ReLU at three inputs

The ReLU is $\max(z, 0)$ . Its value at $z = -2$ is ____.

进入交互式练习

免费注册 · 即时批改 · 自动安排间隔复习。

免费开始这门课