English
Related papers

Related papers: Smooth Kolmogorov Arnold networks enabling structu…

200 papers

Hybrid constitutive modeling integrates two complementary approaches for describing and predicting a material's mechanical behavior: purely data-driven black-box methods and physically constrained, theory-based models. While black-box…

Computational Physics · Physics 2025-02-28 Kian P. Abdolazizi , Roland C. Aydin , Christian J. Cyron , Kevin Linka

This paper presents the use of Kolmogorov-Arnold Networks (KANs) for forecasting the CBOE Volatility Index (VIX). Unlike traditional MLP-based neural networks that are often criticized for their black-box nature, KAN offers an interpretable…

Machine Learning · Computer Science 2025-02-04 So-Yoon Cho , Sungchul Lee , Hyun-Gyoon Kim

Data science has emerged as fourth paradigm of scientific exploration. However many machine learning models operate as black boxes offering limited insight into the reasoning behind their predictions. This lack of transparency is one of the…

Machine Learning · Computer Science 2025-01-31 Sudhanva Kulkarni

While accurate, black-box system identification models lack interpretability of the underlying system dynamics. This paper proposes State-Space Kolmogorov-Arnold Networks (SS-KAN) to address this challenge by integrating Kolmogorov-Arnold…

Machine Learning · Computer Science 2025-06-24 Gonçalo Granjal Cruz , Balazs Renczes , Mark C Runacres , Jan Decuyper

Kolmogorov-Arnold Networks (KANs) are emerging as a powerful framework for interpretable and efficient system identification in dynamic systems. By leveraging the Kolmogorov-Arnold representation theorem, KANs enable function approximation…

Machine Learning · Computer Science 2025-06-13 Nart Gashi , Panagiotis Kakosimos , George Papafotiou

The ``black-box'' nature of deep learning models presents a significant barrier to their adoption for scientific discovery, where interpretability is paramount. This challenge is especially pronounced in discovering the governing equations…

Machine Learning · Computer Science 2025-08-26 Riccardo Cappi , Paolo Frazzetto , Nicolò Navarin , Alessandro Sperduti

This paper explores uncertainty quantification (UQ) methods in the context of Kolmogorov-Arnold Networks (KANs). We apply an ensemble approach to KANs to obtain a heuristic measure of UQ, enhancing interpretability and robustness in…

Machine Learning · Computer Science 2025-04-22 Amirhossein Mollaali , Christian Bolivar Moya , Amanda A. Howard , Alexander Heinlein , Panos Stinis , Guang Lin

Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability, making their application challenging in domains requiring transparent decision-making. We propose the Graph Kolmogorov-Arnold Network…

Machine Learning · Computer Science 2025-06-02 Gianluca De Carlo , Andrea Mastropietro , Aris Anagnostopoulos

Kolmogorov-Arnold Networks (KANs) are a recently introduced neural architecture that replace fixed nonlinearities with trainable activation functions, offering enhanced flexibility and interpretability. While KANs have been applied…

Machine Learning · Computer Science 2026-03-31 Spyros Rigas , Dhruv Verma , Georgios Alexandridis , Yixuan Wang

For many real-world applications, understanding feature-outcome relationships is as crucial as achieving high predictive accuracy. While traditional neural networks excel at prediction, their black-box nature obscures underlying functional…

Machine Learning · Computer Science 2025-10-03 Wangxuan Fan , Ching Wang , Siqi Li , Nan Liu

This work introduces Probabilistic Kolmogorov-Arnold Network (P-KAN), a novel probabilistic extension of Kolmogorov-Arnold Networks (KANs) for time series forecasting. By replacing scalar weights with spline-based functional connections and…

Machine Learning · Computer Science 2025-10-21 Cristian J. Vaca-Rubio , Roberto Pereira , Luis Blanco , Engin Zeydan , Màrius Caus

This study explores the application of Kolmogorov-Arnold Networks (KANs) in predicting nuclear binding energies, leveraging their ability to decompose complex multi-parameter systems into simpler univariate functions. By utilizing data from…

Nuclear Theory · Physics 2025-02-10 Hao Liu , Jin Lei , Zhongzhou Ren

Time series forecasting has long been a focus of research across diverse fields, including economics, energy, healthcare, and traffic management. Recent works have introduced innovative architectures for time series models, such as the…

Machine Learning · Computer Science 2025-03-28 Young-Chae Hong , Bei Xiao , Yangho Chen

The Kolmogorov-Arnold Network (KAN) has emerged as a promising neural network architecture for small-scale AI+Science applications. However, it suffers from inflexibility in modeling ridge functions, which is widely used in representing the…

Computational Physics · Physics 2025-04-10 Zhiteng Zhou , Zhaoyue Xu , Yi Liu , Shizhao Wang

We present a novel approach to predicting the pressure and flow rate of flexible electrohydrodynamic pumps using the Kolmogorov-Arnold Network. Inspired by the Kolmogorov-Arnold representation theorem, KAN replaces fixed activation…

Machine Learning · Computer Science 2024-12-31 Yanhong Peng , Yuxin Wang , Fangchao Hu , Miao He , Zebing Mao , Xia Huang , Jun Ding

Kolmogorov-Arnold Networks (KANs) have gained attention for their potential to outperform Multi-Layer Perceptrons (MLPs) in terms of parameter efficiency and interpretability. Unlike traditional MLPs, KANs use learnable non-linear…

Hardware Architecture · Computer Science 2026-03-19 Sohaib Errabii , Olivier Sentieys , Marcello Traiola

With increasing penetration of distributed energy resources installed behind the meter, there is a growing need for adequate modelling of composite loads to enable accurate power system simulation analysis. Existing measurement based load…

Systems and Control · Electrical Eng. & Systems 2025-08-28 Sonam Dorji , Yongkang Sun , Yuchen Zhang , Ghavameddin Nourbakhsh , Yateendra Mishra , Yan Xu

Physics-Informed Neural Networks (PINNs) have emerged as a promising method for solving partial differential equations (PDEs) in scientific computing. While PINNs typically use multilayer perceptrons (MLPs) as their underlying architecture,…

Machine Learning · Computer Science 2024-11-12 Bruno Jacob , Amanda A. Howard , Panos Stinis

Due to their effective performance, Convolutional Neural Network (CNN) and Vision Transformer (ViT) architectures have become the standard for solving computer vision tasks. Such architectures require large data sets and rely on convolution…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Jorge Luiz dos Santos Canuto , Linnyer Beatrys Ruiz Aylon , Rodrigo Clemente Thom de Souza

Kolmogorov-Arnold Networks (KANs) require significantly smaller architectures compared to multilayer perceptron (MLP)-based approaches, while retaining expressive power through spline-based activations. Moving boundary problems are…

Mathematical Physics · Physics 2026-02-10 Tarus Pande , V M S K Minnikanti , Shyamprasad Karagadde