Hard Sigmoid

Introduced by Courbariaux et al. in BinaryConnect: Training Deep Neural Networks with binary weights during propagations

The Hard Sigmoid is an activation function used for neural networks of the form:

$$f\left(x\right) = \max\left(0, \min\left(1,\frac{\left(x+1\right)}{2}\right)\right)$$

Source: BinaryConnect: Training Deep Neural Networks with binary weights during propagations

Read Paper See Code

Paper	Code	Results	Date	Stars

This feature is experimental; we are continuously improving our matching algorithm.

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign