APTx: better activation function than MISH, SWISH, and ReLU's variants used in deep learning

TL;DR

This paper introduces APTx, a new activation function that performs similarly to MISH but with fewer computations, leading to faster training and lower hardware demands in deep learning models.

Contribution

The paper proposes APTx, a novel activation function that reduces computational complexity while maintaining performance comparable to MISH.

Findings

APTx speeds up model training compared to MISH.

APTx requires fewer mathematical operations.

APTx reduces hardware requirements for deep learning models.

Abstract

Activation Functions introduce non-linearity in the deep neural networks. This nonlinearity helps the neural networks learn faster and efficiently from the dataset. In deep learning, many activation functions are developed and used based on the type of problem statement. ReLU's variants, SWISH, and MISH are goto activation functions. MISH function is considered having similar or even better performance than SWISH, and much better than ReLU. In this paper, we propose an activation function named APTx which behaves similar to MISH, but requires lesser mathematical operations to compute. The lesser computational requirements of APTx does speed up the model training, and thus also reduces the hardware requirement for the deep learning model. Source code: https://github.com/mr-ravin/aptx_activation