Porovnat metody

	Kolmogorov-Arnoldovy sítě	Vision Transformer
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2024	2021
Tvůrce	Ziming Liu	Dosovitskiy, A. et al.
Typ	Neural network architecture	Transformer architecture for images (self-attention over patches)
Původní zdroj	Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Soljačić, M., Hou, T. Y., & Tegmark, M. (2024). KAN: Kolmogorov-Arnold Networks. arXiv preprint arXiv:2404.19756.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Další názvy	KAN, Kolmogorov-Arnold	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Příbuzné	4	5
Shrnutí	Kolmogorov-Arnold Networks (KAN) is a neural network architecture introduced by Liu et al. in 2024 that replaces linear transformations with learned univariate functions on edges. Inspired by the Kolmogorov-Arnold representation theorem, KAN achieves superior function approximation with fewer parameters than traditional MLPs, offering potential efficiency gains and improved interpretability.	The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).