English
Related papers

Related papers: FS-KAN: Permutation Equivariant Kolmogorov-Arnold …

200 papers

Kolmogorov-Arnold Networks or KANs have shown the ability to outperform classical Deep Neural Networks, while using far fewer trainable parameters for regression problems on scientific domains. Even more powerful has been their…

Federated Kolmogorov-Arnold Networks (F-KANs) have already been proposed, but their assessment is at an initial stage. We present a comparison between KANs (using B-splines and Radial Basis Functions as activation functions) and Multi-…

Machine Learning · Computer Science 2024-10-14 Arthur Mendonça Sasse , Claudio Miceli de Farias

Kolmogorov-Arnold Networks (KANs), a novel type of neural network, have recently gained popularity and attention due to the ability to substitute multi-layer perceptions (MLPs) in artificial intelligence (AI) with higher accuracy and…

Kolmogorov--Arnold Networks (KANs) have recently attracted attention as edge-based neural architectures in which learnable univariate functions replace conventional fixed activation functions. A key source of flexibility in KANs is the…

Computational Engineering, Finance, and Science · Computer Science 2026-05-07 Amir Noorizadegan , Sifan Wang

Kolmogorov-Arnold Networks (KANs) have recently shown promise for solving partial differential equations (PDEs). Yet their original formulation is computationally and memory intensive, motivating the introduction of Chebyshev Type-I-based…

Machine Learning · Computer Science 2026-01-19 Hangwei Zhang , Zhimu Huang , Yan Wang

The domain of laser fusion presents a unique and challenging predictive modeling application landscape for machine learning methods due to high problem complexity and limited training data. Data-driven approaches utilizing prescribed…

Machine Learning · Computer Science 2024-09-16 Rahman Ejaz , Varchas Gopalaswamy , Riccardo Betti , Aarne Lees , Christopher Kanan

Federated learning (FL), widely used in privacy-critical applications, suffers from limited interpretability, whereas Kolmogorov-Arnold Networks (KAN) address this limitation via learnable spline functions. However, existing FL studies…

Machine Learning · Computer Science 2025-11-04 Seunghun Yu , Youngjoon Lee , Jinu Gong , Joonhyuk Kang

Physics-Informed Neural Networks (PINNs) have emerged as a powerful mesh-free framework for solving ordinary and partial differential equations by embedding the governing physical laws directly into the loss function. However, their…

To address the issue of interpretability in multilayer perceptrons (MLPs), Kolmogorov-Arnold Networks (KANs) are introduced in 2024. However, optimizing KAN structures is labor-intensive, typically requiring manual intervention and…

Neural and Evolutionary Computing · Computer Science 2025-01-30 Quan Long , Bin Wang , Bing Xue , Mengjie Zhang

Kolmogorov-Arnold Networks (KANs) replace scalar weights with per-edge vectors of basis coefficients, thereby increasing expressivity and accuracy while also resulting in a multiplicative increase in parameters and memory. We propose…

Machine Learning · Computer Science 2026-02-10 Matthew Raffel , Adwaith Renjith , Lizhong Chen

This paper introduces the Hierarchical Kolmogorov-Arnold Network (HKAN), a novel network architecture that offers a competitive alternative to the recently proposed Kolmogorov-Arnold Network (KAN). Unlike KAN, which relies on…

Machine Learning · Computer Science 2026-01-21 Grzegorz Dudek , Tomasz Rodak

Scientific discovery and dynamic characterization of the physical system play a critical role in understanding, learning, and modeling the physical phenomena and behaviors in various fields. Although theories and laws of many system…

Optics · Physics 2025-04-29 Xiaotian Jiang , Min Zhang , Xiao Luo , Zelai Yu , Yiming Meng , Danshi Wang

Recurrent Neural Networks (RNNs) have revolutionized many areas of machine learning, particularly in natural language and data sequence processing. Long Short-Term Memory (LSTM) has demonstrated its ability to capture long-term dependencies…

Machine Learning · Computer Science 2025-08-01 Remi Genet , Hugo Inzirillo

We propose a novel approach that enhances multivariate function approximation using learnable path signatures and Kolmogorov-Arnold networks (KANs). We enhance the learning capabilities of these networks by weighting the values obtained by…

Machine Learning · Computer Science 2024-12-10 Hugo Inzirillo , Remi Genet

Artificial Neural Networks (ANNs) have significantly advanced various fields by effectively recognizing patterns and solving complex problems. Despite these advancements, their interpretability remains a critical challenge, especially in…

Machine Learning · Computer Science 2025-11-24 Alejandro Polo-Molina , David Alfaya , Jose Portela

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

The present paper introduces concurrency-driven enhancements to the training algorithm for the Kolmogorov-Arnold networks (KANs) that is based on the Newton-Kaczmarz (NK) method. Prior research shows that KANs trained using the NK-based…

Machine Learning · Computer Science 2026-03-30 Andrew Polar , Michael Poluektov

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

Neural networks have emerged as powerful tools for modeling complex physical systems, yet balancing high accuracy with computational efficiency remains a critical challenge in their convergence behavior. In this work, we propose the Hybrid…

Machine Learning · Computer Science 2025-04-01 Zuyu Xu , Bin Lv

Massive number of applications involve data with underlying relationships embedded in non-Euclidean space. Graph neural networks (GNNs) are utilized to extract features by capturing the dependencies within graphs. Despite groundbreaking…

Machine Learning · Computer Science 2024-06-21 Fan Zhang , Xin Zhang