arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.07906cs.LGcs.AIcs.NAcs.NEmath.NA
收藏

KAN与MLP在不规则或含噪函数上的对比

KAN versus MLP on Irregular or Noisy Functions

School of Information Science and Engineering, Southeast University(东南大学信息科学与工程学院);School of Economics and Management, Southeast University(东南大学经济管理学院)

Chen Zeng, Jiahui Wang, Haoran Shen, Qiao Wang

AI总结:

该研究控制参数与样本量公平对比KAN和MLP在六类不规则或含噪函数上的性能,发现KAN并非始终最优,部分场景下MLP更优或相当,噪声会干扰两类网络提取不规则特征,为后续神经网络研究提供参考。

摘要:

本文对比了Kolmogorov-Arnold Networks(KAN,柯尔莫哥洛夫-阿诺德网络)与Multi-Layer Perceptron(MLP,多层感知机)在不规则或含噪函数上的性能。我们控制参数数量与训练样本规模以确保对比公平。为清晰起见,我们将函数分为六类:正则函数、存在局部不可微点的连续函数、带跳跃间断点的函数、带奇点的函数、存在相干振荡的函数以及含噪函数。实验结果表明,KAN并非始终表现最优;对于部分类型的函数,MLP的表现优于KAN或与之相当。此外,增大训练样本规模可在一定程度上提升性能。当给函数加入噪声后,不规则特征通常会被噪声掩盖,导致MLP与KAN都难以有效提取这些特征。我们希望这些实验能为未来的神经网络研究提供有价值的见解,并推动更多研究来攻克这些挑战。

英文摘要:

In this paper, we compare the performance of Kolmogorov-Arnold Networks (KAN) and Multi-Layer Perceptron (MLP) networks on irregular or noisy functions. We control the number of parameters and the size of the training samples to ensure a fair comparison. For clarity, we categorize the functions into six types: regular functions, continuous functions with local non-differentiable points, functions with jump discontinuities, functions with singularities, functions with coherent oscillations, and noisy functions. Our experimental results indicate that KAN does not always perform best. For some types of functions, MLP outperforms or performs comparably to KAN. Furthermore, increasing the size of training samples can improve performance to some extent. When noise is added to functions, the irregular features are often obscured by the noise, making it challenging for both MLP and KAN to extract these features effectively. We hope these experiments provide valuable insights for future neural network research and encourage further investigations to overcome these challenges.

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。

↑