Easy attention: A simple self-attention mechanism for transformer-based time-series reconstruction and prediction

no code implementations • 24 Aug 2023 • Marcial Sanchis-Agudo, Yuning Wang, Luca Guastoni, Karthik Duraisamy, Ricardo Vinuesa

To improve the robustness of transformer neural networks used for temporal-dynamics prediction of chaotic systems, we propose a novel attention mechanism called easy attention which we demonstrate in time-series reconstruction and prediction.

Temporal Sequences Time Series