Results 151 to 160 of about 2,256,882 (213)

KAN: Kolmogorov-Arnold Networks

International Conference on Learning Representations
Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs).
Ziming Liu, Yixuan Wang, Sachin Vaidya, Fabian Ruehle, James Halverson, Marin Soljacic, Thomas Y. Hou, Max Tegmark   +7 more
semanticscholar   +1 more source

U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

AAAI Conference on Artificial Intelligence
U-Net has become a cornerstone in various visual applications such as image segmentation and diffusion probability models. While numerous innovative designs and improvements have been introduced by incorporating transformers or MLPs, the networks are ...
Chenxin Li, Xinyu Liu, Wuyang Li, Cheng Wang, Hengyu Liu, Yixuan Yuan   +5 more
semanticscholar   +1 more source

KAN 2.0: Kolmogorov-Arnold Networks Meet Science

arXiv.org
A major challenge of AI + Science lies in their inherent incompatibility: today's AI is primarily based on connectionism, while science depends on symbolism.
Ziming Liu, Pingchuan Ma, Yixuan Wang, Wojciech Matusik, Max Tegmark   +4 more
semanticscholar   +1 more source

A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks

Computer Methods in Applied Mechanics and Engineering
Kolmogorov-Arnold Networks (KANs) were recently introduced as an alternative representation model to MLP. Herein, we employ KANs to construct physics-informed machine learning models (PIKANs) and deep operator models (DeepOKANs) for solving differential ...
K. Shukla, Juan Diego Toscano, Zhicheng Wang, Zongren Zou, G. Karniadakis   +4 more
semanticscholar   +1 more source

KAN or MLP: A Fairer Comparison

arXiv.org
This paper does not introduce a novel method. Instead, it offers a fairer and more comprehensive comparison of KAN and MLP models across various tasks, including machine learning, computer vision, audio processing, natural language processing, and ...
Runpeng Yu, Weihao Yu, Xinchao Wang
semanticscholar   +1 more source

Pattern Recognition Method for Detecting Partial Discharge in Oil-Paper Insulation Equipment Using Optical F-P Sensor Array Based on KAN-CNN Algorithm

Journal of Lightwave Technology
Ultrasound detection can promptly identify partial discharge (PD) faults inside power transformer by using fiber-optic Fabry-Perot (F-P) array sensors.
Hong Liu, Zhixian Zhang, Ruimin Song, Zhiqing Shu, Jianxin Wang, Haoyuan Tian, Yuxuan Song, Weigen Chen   +7 more
semanticscholar   +1 more source

A Hybrid KAN-BiLSTM Transformer with Multi-Domain Dynamic Attention Model for Cybersecurity

Technologies
With the exponential growth of cyberbullying cases on social media, there is a growing need to develop effective mechanisms for its detection and prediction, which can create a safer and more comfortable digital environment.
Aleksandr Chechkin, Ekaterina S. Pleshakova, S. Gataullin   +2 more
semanticscholar   +1 more source

TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting

International Conference on Learning Representations
Real-world time series often have multiple frequency components that are intertwined with each other, making accurate time series forecasting challenging.
Songtao Huang, Zhen Zhao, Can Li, Lei Bai   +3 more
semanticscholar   +1 more source

BSRBF-KAN: A combination of B-splines and Radial Basic Functions in Kolmogorov-Arnold Networks

arXiv.org
In this paper, we introduce BSRBF-KAN, a Kolmogorov Arnold Network (KAN) that combines B-splines and radial basis functions (RBFs) to fit input vectors during data training.
Hoang Thang Ta
semanticscholar   +1 more source