Comparer des méthodes

	TimeGPT	Mamba (Modèle à espace d'états)	Vision Transformer
Domaine	Apprentissage profond	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2023	2023	2021
Auteur d'origine	Fabio Garza	Albert Gu	Dosovitskiy, A. et al.
Type	Neural network architecture	Neural network architecture	Transformer architecture for images (self-attention over patches)
Source fondatrice	Garza, F., & White, C. W. (2023). TimeGPT-1: A Time Series Foundation Model. In ICML 2024 Time Series Workshop.	Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Alias	TimeGPT-1, Time series GPT	Mamba, State space models, Selective state space	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Apparentées	4	4	5
Résumé	TimeGPT is a time series foundation model introduced by Garza and White in 2023 that unifies forecasting, anomaly detection, and classification in a single pre-trained model. Inspired by large language models, TimeGPT is pre-trained on diverse time series and transfers well to downstream tasks with minimal fine-tuning.	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.	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).