arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2501.06389cs.LGcs.AIcs.NE

Kolmogorov-Arnold网络用于金属表面缺陷分类

Kolmogorov-Arnold networks for metal surface defect classification

AGH University of Krakow(克拉科夫AGH大学);Systems Research Institute, Polish Academy of Sciences(波兰科学院系统研究所);University of Technology Sydney(悉尼科技大学);Óbuda University(欧布达大学);NASK National Research Institute(NASK国家研究院)

Maciej Krzywda, Mariusz Wermiński, Szymon Łukasik, Amir H. Gandomi

AI总结:

本文提出用Kolmogorov-Arnold网络(KAN)分类钢材表面缺陷,相比MLP和CNN,KAN以更少参数实现更高精度和更快收敛,提升图像分类性能。

摘要:

本文介绍了Kolmogorov-Arnold网络(KAN)在金属表面缺陷分类中的应用。具体而言,对钢材表面进行分析,以检测裂纹、夹杂物、斑块、麻点表面和划痕等缺陷。基于Kolmogorov-Arnold定理,KAN提供了一种相较于传统多层感知器(MLPs)的新方法,通过利用样条函数实现更高效的函数逼近。结果表明,KAN网络能以更少的参数达到比卷积神经网络(CNNs)更高的准确率,从而在图像分类中实现更快的收敛和更好的性能。

英文摘要:

This paper presents the application of Kolmogorov-Arnold Networks (KAN) in classifying metal surface defects. Specifically, steel surfaces are analyzed to detect defects such as cracks, inclusions, patches, pitted surfaces, and scratches. Drawing on the Kolmogorov-Arnold theorem, KAN provides a novel approach compared to conventional multilayer perceptrons (MLPs), facilitating more efficient function approximation by utilizing spline functions. The results show that KAN networks can achieve better accuracy than convolutional neural networks (CNNs) with fewer parameters, resulting in faster convergence and improved performance in image classification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑