SAU: Smooth activation function using convolution with approximate identities

09/27/2021

∙

by   Koushik Biswas, et al.

∙

0

∙

share

Well-known activation functions like ReLU or Leaky ReLU are non-differentiable at the origin. Over the years, many smooth approximations of ReLU have been proposed using various smoothing techniques. We propose new smooth approximations of a non-differentiable activation function by convolving it with approximate identities. In particular, we present smooth approximations of Leaky ReLU and show that they outperform several well-known activation functions in various datasets and models. We call this function Smooth Activation Unit (SAU). Replacing ReLU by SAU, we get 5.12 ShuffleNet V2 (2.0x) model on CIFAR100 dataset.