Krahasoni metodat

	Rrjetet Kolmogorov-Arnold	Vision Transformer
Fusha	Mësimi i thellë	Mësimi i thellë
Familja	Machine learning	Machine learning
Viti i origjinës	2024	2021
Krijuesi	Ziming Liu	Dosovitskiy, A. et al.
Lloji	Neural network architecture	Transformer architecture for images (self-attention over patches)
Burimi themelues	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.
Emërtime të tjera	KAN, Kolmogorov-Arnold	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Të lidhura	4	5
Përmbledhja	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).