Tanhsoft A Family Of Activation Functions Combining Tanh And Softplus

# TanhSoft -- a family of activation functions combining Tanh and Softplus

**arXiv ID:** 2009.03863
**Authors:** Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey
**Published:** 2020-09-08T16:59:28Z
**Abstract:**
Deep learning at its core, contains functions that are composition of a linear transformation with a non-linear function known as activation function. In past few years, there is an increasing interest in construction of novel activation functions resulting in better learning. In this work, we propose a family of novel activation functions, namely TanhSoft, with four undetermined hyper-parameters of the form tanh(αx+βe^{γx})ln(δ+e^x) and tune these hyper-parameters to obtain activation functions which are shown to outperform several well known activation functions. For instance, replacing ReLU with xtanh(0.6e^x)improves top-1 classification accuracy on CIFAR-10 by 0.46% for DenseNet-169 and 0.7% for Inception-v3 while with tanh(0.87x)ln(1 +e^x) top-1 classification accuracy on CIFAR-100 improves by 1.24% for DenseNet-169 and 2.57% for SimpleNet model.

## Skill Description

This skill is generated from the arXiv paper: TanhSoft -- a family of activation functions combining Tanh and Softplus (2009.03863).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2009.03863](http://arxiv.org/abs/2009.03863v1)