Linganisha mbinu

	Miamala ya Kolmogorov-Arnold	Mamba (Muundo wa Nafasi ya Hali)	Autoenkoda Zilizofunikwa	Transformer wa Maono
Nyanja	Ujifunzaji wa Kina	Ujifunzaji wa Kina	Ujifunzaji wa Kina	Ujifunzaji wa Kina
Familia	Machine learning	Machine learning	Machine learning	Machine learning
Mwaka wa asili	2024	2023	2021	2021
Mwanzilishi	Ziming Liu	Albert Gu	Kaiming He	Dosovitskiy, A. et al.
Aina	Neural network architecture	Neural network architecture	Neural network architecture	Transformer architecture for images (self-attention over patches)
Chanzo asilia	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.	Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956.	He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Majina mbadala	KAN, Kolmogorov-Arnold	Mamba, State space models, Selective state space	MAE, Vision MAE	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Zinazohusiana	4	4	4	5
Muhtasari	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.	Mamba is a sequence model architecture introduced by Gu and Dao in 2023 that achieves linear-time complexity while maintaining strong performance on language modeling tasks. By combining state space models with input-dependent selectivity, Mamba addresses the quadratic complexity of transformers while preserving modeling power.	Masked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels.	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).