2014
EMSS 2014 Proceeding
Evolutionary algorithms for hyperparameter tuning on neural networks models
Authors: David Orive, Gorka Sorrosal, Cruz E. Borges, Cristina Martin, 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.
I3M Scientific Sponsors
I3M Industrial Sponsors
I3M Media Sponsors
