Módszerek összehasonlítása

	N-BEATSx	Vision Transformer
Tudományterület	Mélytanulás	Mélytanulás
Módszercsalád	Machine learning	Machine learning
Keletkezés éve	2023	2021
Megalkotó	Cristian Challu	Dosovitskiy, A. et al.
Típus	Neural network architecture	Transformer architecture for images (self-attention over patches)
Alapmű	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.
Alternatív nevek	N-BEATSx, NBEATS-x	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Kapcsolódó	4	5
Összefoglaló	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).