Shifted Hexpo activation function: An improved vanishing gradient mitigation activation function for disease classification

Shifted Hexpo activation function: An improved vanishing gradient mitigation activation function for disease classification

Activation functions (AFs) in deep learning significantly impacts model performance. In this study, we proposed Shifted Hexpo (SHexpo), an improved variant of the Hexpo AF, designed to address limitations such as vanishing gradients and parameter sensitivity. SHexpo introduces a shifting parameter,...

Full description

Saved in:
Bibliographic Details
Main Authors: Joseph Otoo, Suleman Nasiru, Irene Dekomwine Angbing
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Machine Learning with Applications
Subjects:
Convolutional neural network
Activation function
Cervical cancer
Hexpo
Deep learning
Medical image classifications
Online Access:http://www.sciencedirect.com/science/article/pii/S2666827025000349
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Activation functions (AFs) in deep learning significantly impacts model performance. In this study, we proposed Shifted Hexpo (SHexpo), an improved variant of the Hexpo AF, designed to address limitations such as vanishing gradients and parameter sensitivity. SHexpo introduces a shifting parameter, enhancing its adaptability and performance across diverse data distributions. Using ResNet 101, DenseNet 169, 5 and 10-layer lightweight Convolutional Neural Network (CNN) trained on the SIPaKMeD dataset for cervical cancer classification, we compared SHexpo against Hexpo, ReLU, Swish, Mish, GELU and PReLU under four pre-processing techniques: zero-mean centering, normalization, their combination and ImageNet weights. Our results demonstrate that SHexpo achieves higher classification accuracy and better gradient stability than Hexpo while performing competitively with state-of-the-art AFs. Our findings indicate that SHexpo can be effectively integrated into both lightweight and deep architectures. Additionally, Grad-CAM visualizations highlight SHexpo’s capability to enhance interpretability by localizing the most relevant image regions contributing to model predictions. These results demonstrate SHexpo’s potentials for medical image analysis in low-resource settings.
ISSN:2666-8270

Similar Items