Types of activation functions supported in MxNet?


#1

What are the different types of activation functions supported in MxNet?

  • relu
  • tanh
  • ?

#2

Found it in: src/operator/nn/activation.cc

The following activation functions are supported:

- `relu`: Rectified Linear Unit, :math:`y = max(x, 0)`
- `sigmoid`: :math:`y = \frac{1}{1 + exp(-x)}`
- `tanh`: Hyperbolic tangent, :math:`y = \frac{exp(x) - exp(-x)}{exp(x) + exp(-x)}`
- `softrelu`: Soft ReLU, or SoftPlus, :math:`y = log(1 + exp(x))`
- `softsign`: :math:`y = \frac{x}{1 + abs(x)}`