Authors:
David Orive Miguel, Gorka Sorrosal Yarritu, Cruz Enrique Borges Hernández, Cristina Martín Andonegui, Ainhoa Alonso Vicario

Abstract:

In this work we present a comparison of several Artificial Neural Networks weights initialization methods based on Evolutionary Algorithms. We have tested these methods on three datasets: KEEL regression problems, random synthetic dataset and a dataset of concentration of different chemical species from the Bioethanol To Olefins process. Results demonstrated that the tuning of neural networks initial weights improves significantly their performance compared to a random initialization. In addition, several crossover algorithms were tested to identify the best one for the present objective. In the post-hoc analysis there were found significant differences between the implemented crossover algorithms when the network has four or more inputs.



Proceedings: Proceedings of the 26th European Modeling & Simulation Symposium
Presented at:

EMSS (2014)


ISBN:

978-88-97999-38-6


Year:

2014


Citation
David Orive Miguel, Gorka Sorrosal Yarritu, Cruz Enrique Borges Hernández, Cristina Martín Andonegui, Ainhoa Alonso Vicario. (2014) "Evolutionary Algorithms for Hyperparameter Tuning on Neural Networks Models" In Proceedings of the 26th European Modeling & Simulation Symposium.