Transformers in Time-series Analysis: A Tutorial
| Autor: | Ahmed, Sabeen, Nielsen, Ian E., Tripathi, Aakash, Siddiqui, Shamoon, Rasool, Ghulam, Ramachandran, Ravi P. |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| DOI: | 10.1007/s00034-023-02454-8 |
| Popis: | Transformer architecture has widespread applications, particularly in Natural Language Processing and computer vision. Recently Transformers have been employed in various aspects of time-series analysis. This tutorial provides an overview of the Transformer architecture, its applications, and a collection of examples from recent research papers in time-series analysis. We delve into an explanation of the core components of the Transformer, including the self-attention mechanism, positional encoding, multi-head, and encoder/decoder. Several enhancements to the initial, Transformer architecture are highlighted to tackle time-series tasks. The tutorial also provides best practices and techniques to overcome the challenge of effectively training Transformers for time-series analysis. Comment: 28 pages, 17 figures |
| Databáze: | arXiv |
| Externí odkaz: |
|