Costa, Samuel SampaioPato, MatildeDatia, Nuno2025-05-272025-05-272025-03-039798400718014PURE: 116901682PURE UUID: 4311e018-0a28-407d-a090-eddf04d6a753Scopus: 105000414854http://hdl.handle.net/10362/183535Publisher Copyright: © 2024 Copyright held by the owner/author(s).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.7361416engClassificationHuman Activity RecognitionKernel functionKolmogorov-Arnold NetworksMultivariate functionsArtificial Intelligenceconference object10.1145/3704137.3704166https://www.scopus.com/pages/publications/105000414854