lsl1229840757

训练神经网络(上)——激活函数、数据 预处理

Activateion

Sigmoid

σ ( x ) = 1 1 + e − x \sigma(x) = \frac{1}{1 + e^{-x}} σ(x)=1+ex1

  • Squashes numbers to range [0,1]
  • Historically popular

3 problems:

  1. Saturated neurons kill the gradient
  2. Sigmoid outputs are not zero-centered
  3. exp() is a bit compute expensive

tanh(x)

  • Squanshes numbers to range [-1, 1]
  • zero centered

分类:

技术点:

相关文章:

  • 2021-06-02
  • 2022-12-23
  • 2022-12-23
  • 2022-12-23
  • 2022-12-23
  • 2021-05-18
  • 2021-12-03
  • 2021-07-20
猜你喜欢
  • 2022-12-23
  • 2021-05-25
  • 2021-09-10
  • 2021-09-07
  • 2022-12-23
  • 2022-12-23
  • 2022-12-23
相关资源
相似解决方案