Curvature-Informed Attention Mechanism for Long Short-Term Memory Networks

Lynda Ayachi

2024

Abstract

Time series forecasting is a crucial task across diverse domains, and recent research focuses on refining model architectures for enhanced predictive capabilities. In this paper, we introduce a novel approach by integrating curvature measures into an attention mechanism alongside Long Short-Term Memory (LSTM) networks. The objective is to improve the interpretability and overall performance of time series forecasting models. The proposed Curvature-Informed Attention Mechanism (CIAM) enhances learning by personalizing the weight attribution within the attention mechanism. Through comprehensive experimental evaluations on real-world datasets, we demonstrate the efficacy of our approach, showcasing competitive forecasting accuracy compared to traditional LSTM models.

Paper Citation

in Harvard Style

Ayachi L. (2024). Curvature-Informed Attention Mechanism for Long Short-Term Memory Networks. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 1263-1269. DOI: 10.5220/0012463500003636

in Bibtex Style

@conference{icaart24,
author={Lynda Ayachi},
title={Curvature-Informed Attention Mechanism for Long Short-Term Memory Networks},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={1263-1269},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012463500003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Curvature-Informed Attention Mechanism for Long Short-Term Memory Networks
SN - 978-989-758-680-4
AU - Ayachi L.
PY - 2024
SP - 1263
EP - 1269
DO - 10.5220/0012463500003636
PB - SciTePress