Work

Bessel-type Activation Functions in Neural Networks

Year: 2025

Type: conference-paper

Abstract: This paper introduces a novel family of activation functions using hypergeometric functions with trainable parameters. Hypergeo-metric functions possess a complex series structure that may create numerical issues. Therefore, we focus on Bessel-type functions of the first kind. The Bessel functions are a subfamily of hypergeometric functions, with characteristics similar to ReLU and sinusoidal activation functions. We investigate the performance of Bessel functions as activation functions within Convolutional Neural Networks (CNNs). Comparative analyses are conducted against established activation functions such as ReLU and sigmoid on benchmark datasets, including MNIST, Happy House, and CIFAR-10. This research aims to explore the potential of Bessel functions as a general class of parametric activation functions adaptable to diverse network architectures.

Source: Procedia Computer Science

DOI: 10.1016/j.procs.2025.07.123

Authors: D. Martins, N. Vieira, T. Slavov, P. Georgieva

Institution: University of Aveiro

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: European Commission, Ministério da Ciência, Tecnologia e Ensino Superior, Center for Research and Development in Mathematics and Applications, Fundação para a Ciência e a Tecnologia