Comparer des méthodes

	TimeGPT	N-BEATSx	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	Cristian Challu	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.	Challu, C., Olivares, K. Q., Oreshkin, B., Garza, F., Mergenthaler-Canseco, M., & Dubrawski, A. (2023). N-BEATSx: Neural Basis Expansion Analysis for Interpretable Time Series Forecasting. In ICLR 2023 Workshop on Multimodal Learning for Science (p. 4).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Alias	TimeGPT-1, Time series GPT	N-BEATSx, NBEATS-x	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.	N-BEATSx is an extension of the N-BEATS neural time series forecasting model that incorporates exogenous (external) variables through a cross-learner architecture. Published in 2023, N-BEATSx improves upon N-BEATS by enabling the model to leverage additional features beyond the historical time series values.	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).