Article
Version 1
Preserved in Portico This version is not peer-reviewed
Evaluating Kolmogorov–Arnold Networks for Scientific Discovery: A Simple Yet Effective Approach
Version 1
: Received: 14 August 2024 / Approved: 15 August 2024 / Online: 19 August 2024 (18:13:54 CEST)
How to cite: Sun, J. Evaluating Kolmogorov–Arnold Networks for Scientific Discovery: A Simple Yet Effective Approach. Preprints 2024, 2024081184. https://doi.org/10.20944/preprints202408.1184.v1 Sun, J. Evaluating Kolmogorov–Arnold Networks for Scientific Discovery: A Simple Yet Effective Approach. Preprints 2024, 2024081184. https://doi.org/10.20944/preprints202408.1184.v1
Abstract
Kolmogorov–Arnold Network (KAN) is an emerging interpretable neural network compared to fully black-box MLPs. Recently, emerging works focus on comprehensive and fair comparisons between KAN and MLP in various tasks. However, these works didn't focus on the strongest advantage of KAN: generating symbolic outputs. The ability of KAN to provide scientific insights or even discover new science is under-examined. In this work, we propose several novel metrics to measure how well a KAN performs on symbolic function fitting: R^2-Mean, weighted R^2-complexity loss, and ranking metrics. We also propose a metric to determine mathematical complexity of a target function and evaluate KAN with several functions of different mathematical complexity. Additionally, we also tried inputs with different ranges to find the effect of normalization.
Keywords
Machine Learning; Neural Networks; Interpretable AI; AI4Science
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment