Work

An empirical study on the application of KANs for classification

Year: 2024

Type: conference-paper

Abstract: Kolmogorov-Arnold Networks (KANs) represent a breakthrough in deep learning, diverging from Multi-Layer Perceptrons (MLPs) by generalizing the Kolmogorov-Arnold representation theorem (KAT) to networks of arbitrary depth and width. This theorem facilitates the decomposition of multivariate functions into constituent one-dimensional elements, with learnable activation functions on weights and the sum operator on nodes. KANs have been shown to exhibit robust performance in function approximation, validated across mathematical, physical, and practical domains such as traffic prediction and medical diagnostics. Our study investigates KANs' efficacy through comprehensive evaluations on OpenML, Kaggle and UCI datasets, with a focus on enhancing Human Activity Recognition systems. They demonstrate high classification performance compared to conventional machine learning approaches and MLPs. These findings underscore KANs' potential as scalable, interpretable tools in modern machine learning applications given their favorable neural scaling laws.

Source: International Conference on Advances in Artificial Intelligence (ICAAI)

DOI: 10.1145/3704137.3704166

Authors: Samuel Sampaio Costa, Matilde Pato, Nuno Datia

Institutions: Universidade Politécnica de Lisboa, University of Lisbon, Laboratório de Sistemas Informáticos de Grande Escala, Laboratório para a Ciência da Computação e Informática

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: NOVA Laboratory for Computer Science and Informatics, Fundação para a Ciência e a Tecnologia