MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders

Authors: Dimanov, D., Balaguer-Ballester, E., Rostami, S. and Singleton, C.

Conference: ICLR2021,2nd Workshop on Neural Architecture Search (NAS 21).

Dates: 7 May 2021

Place of Publication: In press.

https://eprints.bournemouth.ac.uk/35800/

Source: Manual

MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders

Authors: Dimanov, D., Balaguer-Ballester, E., Rostami, S. and Singleton, C.

Conference: ICLR2021: 2nd Workshop on Neural Architecture Search (NAS 21)

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.

https://eprints.bournemouth.ac.uk/35800/

Source: BURO EPrints