Hysteresis Activation Function for Efficient Inference

TL;DR

This paper introduces HeLU, a hysteresis-based activation function that mitigates the dying ReLU problem, improves generalization, and maintains hardware efficiency for neural network inference.

Contribution

The paper proposes HeLU, a novel hysteresis activation function that refines backpropagation and enhances model performance without added complexity.

Findings

HeLU improves model generalization across datasets.

HeLU addresses the dying ReLU problem effectively.

HeLU maintains hardware efficiency during inference.

Abstract

The widely used ReLU is favored for its hardware efficiency, {as the implementation at inference is a one bit sign case,} yet suffers from issues such as the ``dying ReLU'' problem, where during training, neurons fail to activate and constantly remain at zero, as highlighted by Lu et al. Traditional approaches to mitigate this issue often introduce more complex and less hardware-friendly activation functions. In this work, we propose a Hysteresis Rectified Linear Unit (HeLU), an efficient activation function designed to address the ``dying ReLU'' problem with minimal complexity. Unlike traditional activation functions with fixed thresholds for training and inference, HeLU employs a variable threshold that refines the backpropagation. This refined mechanism allows simpler activation functions to achieve competitive performance comparable to their more complex counterparts without introducing unnecessary complexity or requiring inductive biases. Empirical evaluations demonstrate that HeLU enhances model generalization across diverse datasets, offering a promising solution for efficient and effective inference suitable for a wide range of neural network architectures.