Comparer des méthodes

	Réseaux de Kolmogorov-Arnold	Champs de radiance neuronaux (NeRF)	Vision Transformer
Domaine	Apprentissage profond	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2024	2020	2021
Auteur d'origine	Ziming Liu	Ben Mildenhall	Dosovitskiy, A. et al.
Type	Neural network architecture	Neural network architecture	Transformer architecture for images (self-attention over patches)
Source fondatrice	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.	Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2020). NeRF: Representing scenes as neural radiance fields for view synthesis. In Computer Vision-ECCV 2020: 16th European Conference (pp. 405-421). Springer International Publishing.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Alias	KAN, Kolmogorov-Arnold	NeRF, Neural radiance field	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Apparentées	4	4	5
Résumé	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.	Neural Radiance Fields (NeRF) is a method introduced by Mildenhall et al. in 2020 that represents a 3D scene as a continuous function parameterized by a neural network. Given multi-view images of a scene, NeRF learns to predict the color and density of light rays at any spatial location and viewing angle, enabling novel view synthesis with photorealistic quality.	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).