Сравнение на методи

	TimeGPT	Vision Transformer
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2023	2021
Създател	Fabio Garza	Dosovitskiy, A. et al.
Тип	Neural network architecture	Transformer architecture for images (self-attention over patches)
Основополагащ източник	Garza, F., & White, C. W. (2023). TimeGPT-1: A Time Series Foundation Model. In ICML 2024 Time Series Workshop.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Други названия	TimeGPT-1, Time series GPT	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Свързани	4	5
Резюме	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.	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).