Trustworthiness Score for Echo State Networks by Analysis of the Reservoir Dynamics
- Enguita-Gonzalez, Jose M. 1
- Garcia-Perez, Diego 1
- Cuadrado-Vega, Abel Alberto 1
- García-Peña, Daniel
- Rodríguez-Ossorio, José Ramón
- Diaz-Blanco, Ignacio 1
-
1
Universidad de Oviedo
info
Argitalpen urtea: 2024
Orrialdeak: 455-460
Biltzarra: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (32th. 2024. Bruges, Bélgica)
Mota: Biltzar ekarpena
Laburpena
Epistemic uncertainty arises from input data areas where models lack exposure during training and may result in significant performance degradation in deployment. Echo State Networks are often used as virtual sensors or digital twins processing temporal input data, so their robustness against this degradation is crucial. This paper addresses this challenge by proposing a score comparing the similarity between the dynamic evolution of the reservoir in training and in inference. This research aims to enhance model confidence and adaptability in evolving circumstances.
Finantzaketari buruzko informazioa
This work is part of Grant PID2020-115401GB-I00 funded by MCIN/AEI/ 10.13039/501100011033.Finantzatzaile
-
Ministerio de Ciencia e Innovación
Spain
- PID2020-115401GB-I00