Výsledky vyhledávání - "Aguilera Martos, Ignacio"

Report

Local Attention Mechanism: Boosting the Transformer Architecture for Long-Sequence Time Series Forecasting

Autor: Aguilera-Martos, Ignacio, Herrera-Poyatos, Andrés, Luengo, Julián, Herrera, Francisco

Transformers have become the leading choice in natural language processing over other deep learning architectures. This trend has also permeated the field of time series analysis, especially for long-horizon forecasting, showcasing promising results

Externí odkaz: http://arxiv.org/abs/2410.03805

Zobrazit plný text záznamu

Report

FLEX: FLEXible Federated Learning Framework

Autor: Herrera, Francisco, Jiménez-López, Daniel, Argente-Garrido, Alberto, Rodríguez-Barroso, Nuria, Zuheros, Cristina, Aguilera-Martos, Ignacio, Bello, Beatriz, García-Márquez, Mario, Luzón, M. Victoria

In the realm of Artificial Intelligence (AI), the need for privacy and security in data processing has become paramount. As AI applications continue to expand, the collection and handling of sensitive data raise concerns about individual privacy prot

Externí odkaz: http://arxiv.org/abs/2404.06127

Zobrazit plný text záznamu

Report

TSFEDL: A Python Library for Time Series Spatio-Temporal Feature Extraction and Prediction using Deep Learning (with Appendices on Detailed Network Architectures and Experimental Cases of Study)

Autor: Aguilera-Martos, Ignacio, García-Vico, Ángel M., Luengo, Julián, Damas, Sergio, Melero, Francisco J., Valle-Alonso, José Javier, Herrera, Francisco

The combination of convolutional and recurrent neural networks is a promising framework that allows the extraction of high-quality spatio-temporal features together with its temporal dependencies, which is key for time series prediction problems such

Externí odkaz: http://arxiv.org/abs/2206.03179

Zobrazit plný text záznamu