English
Related papers

Related papers: Free-RBF-KAN: Kolmogorov-Arnold Networks with Adap…

200 papers

Multilayer Perceptrons (MLPs) have long been a cornerstone in deep learning, known for their capacity to model complex relationships. Recently, Kolmogorov-Arnold Networks (KANs) have emerged as a compelling alternative, utilizing highly…

Machine Learning · Computer Science 2024-09-17 Farhad Pourkamali-Anaraki

We present a novel approach for verifying properties of Kolmogorov-Arnold Networks (KANs), a class of neural networks characterized by nonlinear, univariate activation functions typically implemented as piecewise polynomial splines or…

Machine Learning · Computer Science 2026-02-09 Noah Schwartz , Chandra Kanth Nagesh , Sriram Sankaranarayanan , Ramneet Kaur , Tuhin Sahai , Susmit Jha

Unlike MLPs, Kolmogorov-Arnold Networks (KANs) expose explicit learnable edge functions on every connection, enabling mechanistic explanation in time-series forecasting. This paper introduces Temporal Functional Circuits, a framework that…

Machine Learning · Computer Science 2026-05-08 Naveen Mysore

Multi-layer perceptrons (MLP's) have been extensively utilized in discovering Deep Koopman operators for linearizing nonlinear dynamics. With the emergence of Kolmogorov-Arnold Networks (KANs) as a more efficient and accurate alternative to…

Machine Learning · Computer Science 2024-08-13 George Nehma , Madhur Tiwari

Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to Multi-layer Perceptrons (MLPs) due to their superior function-fitting abilities in data-driven modeling. In this paper, we propose a novel framework, DAE-KAN, for…

Machine Learning · Computer Science 2025-04-24 Kai Luo , Juan Tang , Mingchao Cai , Xiaoqing Zeng , Manqi Xie , Ming Yan

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…

Kolmogorov-Arnold Networks (KANs) have demonstrated an exceptional ability to learn complex functions on clean, low-dimensional data but struggle to maintain performance on noisy and imperfect real-world datasets. In contrast, conventional…

Traditional neural networks struggle to capture the spectral structure of complex signals. Fourier neural networks (FNNs) attempt to address this by embedding Fourier series components, yet many real-world signals are almost-periodic with…

Machine Learning · Computer Science 2026-04-13 Chen Zeng , Tiehang Xu , Qiao Wang

Kolmogorov-Arnold Networks (KANs) have very recently been introduced into the world of machine learning, quickly capturing the attention of the entire community. However, KANs have mostly been tested for approximating complex functions or…

Machine Learning · Computer Science 2025-01-24 Eleonora Poeta , Flavio Giobergia , Eliana Pastor , Tania Cerquitelli , Elena Baralis

The recently proposed Kolmogorov-Arnold network (KAN) is a promising alternative to multi-layer perceptrons (MLPs) for data-driven modeling. While original KAN layers were only capable of representing the addition operator, the…

Machine Learning · Computer Science 2025-07-28 Benjamin C. Koenig , Suyong Kim , Sili Deng

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

Synthetic Aperture Radar (SAR) image recognition is vital for disaster monitoring, military reconnaissance, and ocean observation. However, large SAR image sizes hinder deep learning deployment on resource-constrained edge devices, and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Pan Yi , Weijie Li , Xiaodong Chen , Jiehua Zhang , Li Liu , Yongxiang Liu

In this work, we employ physics-informed neural operators to map pressure profiles from an input function space to the corresponding bubble radius responses. Our approach employs a two-step DeepONet architecture. To address the intrinsic…

Machine Learning · Computer Science 2025-12-18 Yunhao Zhang , Sidharth S. Menon , Lin Cheng , Aswin Gnanaskandan , Ameya D. Jagtap

In this research, we propose the first approach for integrating the Kolmogorov-Arnold Network (KAN) with various pre-trained Convolutional Neural Network (CNN) models for remote sensing (RS) scene classification tasks using the EuroSAT…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Minjong Cheon

Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet the go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for…

Machine Learning · Computer Science 2026-02-02 Rajib Mostakim , Reza T. Batley , Sourav Saha

Kolmogorov-Arnold Networks (KANs) have recently emerged as a promising alternative to traditional neural architectures, yet their application to speech processing remains under explored. This work presents the first investigation of KANs…

Computation and Language · Computer Science 2025-05-27 Alkis Koudounas , Moreno La Quatra , Eliana Pastor , Sabato Marco Siniscalchi , Elena Baralis

We introduce KAN-GCN, a fast and accurate emulator for ice sheet modeling that places a Kolmogorov-Arnold Network (KAN) as a feature-wise calibrator before graph convolution networks (GCNs). The KAN front end applies learnable…

Machine Learning · Computer Science 2025-10-30 Zesheng Liu , YoungHyun Koo , Maryam Rahnemoonfar

Weight-space models learn directly from the parameters of neural networks, enabling tasks such as predicting their accuracy on new datasets. Naive methods -- like applying MLPs to flattened parameters -- perform poorly, making the design of…

Machine Learning · Computer Science 2026-03-03 Guy Bar-Shalom , Ami Tavory , Itay Evron , Maya Bechler-Speicher , Ido Guy , Haggai Maron

To address the challenge of tractability for optimizing mathematical models in science and engineering, surrogate models are often employed. Recently, a new class of machine learning models named Kolmogorov Arnold Networks (KANs) have been…

Optimization and Control · Mathematics 2025-03-05 Tanuj Karia , Giacomo Lastrucci , Artur M. Schweidtmann

Physics-Informed Neural Networks (PINNs) have emerged as a robust framework for solving Partial Differential Equations (PDEs) by approximating their solutions via neural networks and imposing physics-based constraints on the loss function.…