Détail du document
Identifiant
oai:arXiv.org:2410.05500
Sujet
Computer Science - Computer Vision... Computer Science - Artificial Inte... Computer Science - Machine Learnin... I.2.10 I.4.10 I.4.3 I.4.9Auteur
Yu, Ray Congrui Wu, Sherry Gui, JiangCatégorie
Computer Science
Année
2024
Date de référencement
12/03/2025
Mots clés
network layers science computerRésumé
Despite their immense success, deep neural networks (CNNs) are costly to train, while modern architectures can retain hundreds of convolutional layers in network depth.
Standard convolutional operations are fundamentally limited by their linear nature along with fixed activations, where multiple layers are needed to learn complex patterns, making this approach computationally inefficient and prone to optimization difficulties.
As a result, we introduce RKAN (Residual Kolmogorov-Arnold Network), which could be easily implemented into stages of traditional networks, such as ResNet.
The module also integrates polynomial feature transformation that provides the expressive power of many convolutional layers through learnable, non-linear feature refinement.
Our proposed RKAN module offers consistent improvements over the base models on various well-known benchmark datasets, such as CIFAR-100, Food-101, and ImageNet.
;Comment: Code is available at https://github.com/withray/residualKAN.git
Yu, Ray Congrui,Wu, Sherry,Gui, Jiang, 2024, Residual Kolmogorov-Arnold Network for Enhanced Deep Learning
Hespi: A pipeline for automatically detecting information from hebarium specimen sheets
science recognition institutional detects text-based text pipeline specimen
