Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions

TL;DR

This paper introduces a complex piece-wise linear activation function that improves the performance of both shallow and deep convolutional neural networks compared to traditional ReLU activations.

Contribution

The paper proposes a novel piece-wise linear activation function that outperforms ReLU in CNNs and MLPs, supported by experimental results in PyTorch.

Findings

PWL activations outperform ReLU in CNNs and MLPs

Better accuracy achieved with PWL in shallow and deep networks

Experimental validation on PyTorch benchmarks

Abstract

Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having around 152 layers. Shallow convolution neural networks(CNN's) are still an active research, where some phenomena are still unexplained. Activation functions used in the network are of utmost importance, as they provide non linearity to the networks. Relu's are the most commonly used activation function.We show a complex piece-wise linear(PWL) activation in the hidden layer. We show that these PWL activations work much better than relu activations in our networks for convolution neural networks and multilayer perceptrons. Result comparison in PyTorch for shallow and deep CNNs are given to further strengthen our case.