English
Related papers

Related papers: Automatic Grid Updates for Kolmogorov-Arnold Netwo…

200 papers

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

In the domain of machine learning, the assumption that training and test data share the same distribution is often violated in real-world scenarios, requiring effective out-of-distribution (OOD) detection. This paper presents a novel OOD…

Machine Learning · Computer Science 2025-02-25 Alessandro Canevaro , Julian Schmidt , Mohammad Sajad Marvi , Hang Yu , Georg Martius , Julian Jordan

Kolmogorov-Arnold Networks (KANs) are highly effective in long-term time series forecasting due to their ability to efficiently represent nonlinear relationships and exhibit local plasticity. However, prior research on KANs has…

Machine Learning · Computer Science 2025-06-17 Xiaoyan Kui , Canwei Liu , Qinsong Li , Zhipeng Hu , Yangyang Shi , Weixin Si , Beiji Zou

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

The Kolmogorov-Arnold representation theorem offers a theoretical alternative to Multi-Layer Perceptrons (MLPs) by placing learnable univariate functions on edges rather than nodes. While recent implementations such as Kolmogorov-Arnold…

Machine Learning · Computer Science 2026-01-28 Oscar Eliasson

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 growing need for accurate and efficient 3D identification of tumors, particularly in liver segmentation, has spurred considerable research into deep learning models. While many existing architectures offer strong performance, they often…

Image and Video Processing · Electrical Eng. & Systems 2024-12-30 Bhavesh Gyanchandani , Aditya Oza , Abhinav Roy

Inspired by the Kolmogorov-Arnold representation theorem and Kurkova's principle of using approximate representations, we propose the Kurkova-Kolmogorov-Arnold Network (KKAN), a new two-block architecture that combines robust multi-layer…

Machine Learning · Computer Science 2024-12-24 Juan Diego Toscano , Li-Lian Wang , George Em Karniadakis

We introduce Geometric Kolmogorov--Arnold Networks (GeoKANs), a family of geometry-aware KAN-type models in which approximation is carried out in learned, geometry-adapted coordinates rather than in fixed Euclidean input coordinates. GeoKAN…

Machine Learning · Computer Science 2026-05-11 Abhijit Sen , Bikram Keshari Parida , Giridas Maiti , Mahima Arya , Denys I. Bondar

Despite their immense success, deep convolutional neural networks (CNNs) can be difficult to optimize and costly to train due to hundreds of layers within the network depth. Conventional convolutional operations are fundamentally limited by…

Computer Vision and Pattern Recognition · Computer Science 2025-11-07 Ray Congrui Yu , Sherry Wu , Jiang Gui

Inspired by the Kolmogorov-Arnold superposition theorem, Kolmogorov-Arnold Networks (KANs) have recently emerged as an improved backbone for most deep learning frameworks, promising more adaptivity than their multilayer perceptron (MLP)…

Machine Learning · Computer Science 2025-08-07 Anastasis Kratsios , Bum Jun Kim , Takashi Furuya

The rapid development of deepfake generation techniques necessitates robust face forgery detection algorithms. While methods based on Convolutional Neural Networks (CNNs) and Transformers are effective, there is still room for improvement…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Jiayao Jiang , Bin Liu , Qi Chu , Nenghai Yu

Graph neural networks (GNNs) with attention mechanisms, often referred to as attentive GNNs, have emerged as a prominent paradigm in advanced GNN models in recent years. However, our understanding of the critical process of scoring neighbor…

Machine Learning · Computer Science 2025-03-12 Taoran Fang , Tianhong Gao , Chunping Wang , Yihao Shang , Wei Chow , Lei Chen , Yang Yang

Recent success of graph neural networks (GNNs) in modeling complex graph-structured data has fueled interest in deploying them on resource-constrained edge devices. However, their substantial computational and memory demands present ongoing…

Machine Learning · Computer Science 2026-02-10 Can Cui , Zilong Fu , Penghe Huang , Yuanyuan Li , Wu Deng , Dongyan Li

Characterizing crystalline energy landscapes is essential to predicting thermodynamic stability, electronic structure, and functional behavior. While machine learning (ML) enables rapid property predictions, the "black-box" nature of most…

Disordered Systems and Neural Networks · Physics 2026-04-07 Gen Zu , Ning Mao , Claudia Felser , Yang Zhang

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

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

High-dimensional linear mappings, or linear layers, dominate both the parameter count and the computational cost of most modern deep-learning models. We introduce a general-purpose drop-in replacement, lookup multivariate Kolmogorov-Arnold…

Machine Learning · Computer Science 2025-10-20 Sergey Pozdnyakov , Philippe Schwaller

The discovery of high-performance thermoelectric materials requires models that are both accurate and interpretable. Traditional machine learning approaches, while effective at property prediction, often act as black boxes and provide…

Materials Science · Physics 2025-12-15 Marco Fronzi , Michael J. Ford , Kamal Singh Nayal , Olexandr Isayev , Catherine Stampfl

AI for partial differential equations (PDEs) has garnered significant attention, particularly with the emergence of Physics-informed neural networks (PINNs). The recent advent of Kolmogorov-Arnold Network (KAN) indicates that there is…