MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders
Neural and Evolutionary Computing
2021-06-23 v1 Machine Learning
Abstract
In this paper, we present a novel neuroevolutionary method to identify the architecture and hyperparameters of convolutional autoencoders. Remarkably, we used a hypervolume indicator in the context of neural architecture search for autoencoders, for the first time to our current knowledge. Results show that images were compressed by a factor of more than 10, while still retaining enough information to achieve image classification for the majority of the tasks. Thus, this new approach can be used to speed up the AutoML pipeline for image compression.
Cite
@article{arxiv.2106.11914,
title = {MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders},
author = {Daniel Dimanov and Emili Balaguer-Ballester and Colin Singleton and Shahin Rostami},
journal= {arXiv preprint arXiv:2106.11914},
year = {2021}
}
Comments
Published as a Poster paper in ICLR 2021 Neural Architecture Search workshop