验证柯尔莫哥洛夫-阿诺德网络（Kolmogorov-Arnold Networks）在视觉任务中的有效性
Demonstrating the Efficacy of Kolmogorov-Arnold Networks in Vision Tasks
AI总结：
本研究验证了柯尔莫哥洛夫-阿诺德网络（KAN）在视觉任务中的有效性，通过多数据集实验对比其与主流模型的性能，证明其潜力并填补了相关研究空白。
摘要：
在深度学习领域，柯尔莫哥洛夫-阿诺德网络（Kolmogorov-Arnold Network，KAN）已成为多层感知机（multilayer projections，MLPs）的潜在替代方案。然而，其在视觉任务中的适用性尚未得到广泛验证。在本研究中，我们通过在MNIST、CIFAR10和CIFAR100数据集上开展多组实验（训练批次大小为32），验证了KAN在视觉任务中的有效性。结果表明，KAN在CIFAR10和CIFAR100数据集上的表现优于原始MLP-Mixer，但略逊于当前最优的ResNet-18。这些发现说明KAN在视觉任务中具有巨大潜力，未来可通过进一步改进提升其性能。我们的贡献有三方面：第一，展示了基于KAN的算法在视觉任务中的效率；第二，在多个视觉基准上开展了全面的实证评估，将KAN的性能与MLP-Mixer、卷积神经网络（CNNs）和视觉Transformer（Vision Transformers，ViT）进行对比；第三，首次将原生KAN层应用于视觉任务，填补了以往研究的空白。本文为KAN的后续研究奠定了基础，凸显了其作为图像分类任务可靠替代方案的潜力。
英文摘要：
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 demonstrated the effectiveness of KAN for vision tasks through multiple trials on the MNIST, CIFAR10, and CIFAR100 datasets, using a training batch size of 32. Our results showed that while KAN outperformed the original MLP-Mixer on CIFAR10 and CIFAR100, it performed slightly worse than the state-of-the-art ResNet-18. These findings suggest that KAN holds significant promise for vision tasks, and further modifications could enhance its performance in future evaluations.Our contributions are threefold: first, we showcase the efficiency of KAN-based algorithms for visual tasks; second, we provide extensive empirical assessments across various vision benchmarks, comparing KAN's performance with MLP-Mixer, CNNs, and Vision Transformers (ViT); and third, we pioneer the use of natural KAN layers in visual tasks, addressing a gap in previous research. This paper lays the foundation for future studies on KANs, highlighting their potential as a reliable alternative for image classification tasks.
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。
