中文
相关论文

相关论文: Reimagining Linear Probing: Kolmogorov-Arnold Netw…

200 篇论文

In this paper, we present Convolutional Kolmogorov-Arnold Networks, a novel architecture that integrates the learnable spline-based activation functions of Kolmogorov-Arnold Networks (KANs) into convolutional layers. By replacing…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Alexander Dylan Bodner , Antonio Santiago Tepsich , Jack Natan Spolski , Santiago Pourteau

This systematic review explores the theoretical foundations, evolution, applications, and future potential of Kolmogorov-Arnold Networks (KAN), a neural network model inspired by the Kolmogorov-Arnold representation theorem. KANs…

机器学习 · 计算机科学 2025-06-09 Shriyank Somvanshi , Syed Aaqib Javed , Md Monzurul Islam , Diwas Pandit , Subasish Das

In the realm of deep learning, the Kolmogorov-Arnold Network (KAN) has emerged as a potential alternative to multilayer projections (MLPs). However, its applicability to vision tasks has not been extensively validated. In our study, we…

计算机视觉与模式识别 · 计算机科学 2024-06-24 Minjong Cheon

Tabular data analysis presents unique challenges that arise from heterogeneous feature types, missing values, and complex feature interactions. While traditional machine learning methods like gradient boosting often outperform deep…

机器学习 · 计算机科学 2025-12-10 Ali Eslamian , Alireza Afzal Aghaei , Qiang Cheng

Deep learning models have revolutionized various domains, with Multi-Layer Perceptrons (MLPs) being a cornerstone for tasks like data regression and image classification. However, a recent study has introduced Kolmogorov-Arnold Networks…

机器学习 · 计算机科学 2024-10-04 Mohammadamin Moradi , Shirin Panahi , Erik Bollt , Ying-Cheng Lai

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…

机器学习 · 计算机科学 2025-07-28 Benjamin C. Koenig , Suyong Kim , Sili Deng

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…

计算与语言 · 计算机科学 2025-05-27 Alkis Koudounas , Moreno La Quatra , Eliana Pastor , Sabato Marco Siniscalchi , Elena Baralis

The field of scientific machine learning, which originally utilized multilayer perceptrons (MLPs), is increasingly adopting Kolmogorov-Arnold Networks (KANs) for data encoding. This shift is driven by the limitations of MLPs, including poor…

机器学习 · 计算机科学 2025-11-04 Salah A. Faroughi , Farinaz Mostajeran , Amin Hamed Mashhadzadeh , Shirko Faroughi

Kolmogorov-Arnold Networks (KANs) have gained significant attention as an alternative to traditional multilayer perceptrons, with proponents claiming superior interpretability and performance through learnable univariate activation…

机器学习 · 计算机科学 2025-09-16 Yuntian Hou , Tianrui Ji , Di Zhang , Angelos Stefanidis

Kolmogorov-Arnold Networks (KAN) is a groundbreaking model recently proposed by the MIT team, representing a revolutionary approach with the potential to be a game-changer in the field. This innovative concept has rapidly garnered worldwide…

机器学习 · 计算机科学 2024-06-05 Kunpeng Xu , Lifei Chen , Shengrui Wang

In traditional neural network architectures, a multilayer perceptron (MLP) is typically employed as a classification block following the feature extraction stage. However, the Kolmogorov-Arnold Network (KAN) presents a promising alternative…

计算机视觉与模式识别 · 计算机科学 2024-09-09 Valeriy Lobanov , Nikita Firsov , Evgeny Myasnikov , Roman Khabibullin , Artem Nikonorov

Kolmogorov-Arnold Networks (KANs) are a recent neural network architecture offering an alternative to Multilayer Perceptrons (MLPs) with improved explainability and expressibility. However, KANs are significantly slower than MLPs due to the…

机器学习 · 计算机科学 2026-04-27 Eduardo Said Merin-Martinez , Andres Mendez-Vazquez , Eduardo Rodriguez-Tello

The development of Kolmogorov-Arnold networks (KANs) marks a significant shift from traditional multi-layer perceptrons in deep learning. Initially, KANs employed B-spline curves as their primary basis function, but their inherent…

机器学习 · 计算机科学 2024-06-21 Alireza Afzal Aghaei

Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the Kolmogorov-Arnold Transformer…

机器学习 · 计算机科学 2024-09-18 Xingyi Yang , Xinchao Wang

This paper introduces a novel application of Kolmogorov-Arnold Networks (KANs) to time series forecasting, leveraging their adaptive activation functions for enhanced predictive modeling. Inspired by the Kolmogorov-Arnold representation…

信号处理 · 电气工程与系统科学 2025-10-28 Cristian J. Vaca-Rubio , Luis Blanco , Roberto Pereira , Màrius Caus

Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes ("neurons"), KANs have…

By utilising their adaptive activation functions, Kolmogorov-Arnold Networks (KANs) can be applied in a novel way for the diverse machine learning tasks, including cyber threat detection. KANs substitute conventional linear weights with…

密码学与安全 · 计算机科学 2026-04-01 Mohammed Hassanin

Multilayer Perceptron (MLP), as a simple yet powerful model, continues to be widely used in classification and regression tasks. However, traditional MLPs often struggle to efficiently capture nonlinear relationships in load data when…

机器学习 · 计算机科学 2025-05-13 Yizhou Ma , Zhuoqin Yang , Luis-Daniel Ibáñez

The Convolutional Neural Networks (CNNs) have been the dominant and effective approach for general computer vision tasks. Recently, Kolmogorov-Arnold neural networks (KANs), based on the Kolmogorov-Arnold representation theorem, have shown…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Zhaoxiang Liu , Zhicheng Ma , Kaikai Zhao , Kai Wang , Shiguo Lian

Symbolic neural networks, such as Kolmogorov-Arnold Networks (KAN), offer a promising approach for integrating prior knowledge with data-driven methods, making them valuable for addressing inverse problems in scientific and engineering…

机器学习 · 计算机科学 2024-11-05 Xia Chen , Guoquan Lv , Xinwei Zhuang , Carlos Duarte , Stefano Schiavon , Philipp Geyer
‹ 上一页 1 2 3 10 下一页 ›