MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders

06/07/2021
by   Daniel Dimanov, et al.
0

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.

READ FULL TEXT
research
01/04/2019

Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search

Fabricating neural models for a wide range of mobile devices demands for...
research
10/06/2022

POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique

Automating the research for the best neural network model is a task that...
research
03/01/2017

Lossy Image Compression with Compressive Autoencoders

We propose a new approach to the problem of optimizing autoencoders for ...
research
07/08/2021

Bag of Tricks for Neural Architecture Search

While neural architecture search methods have been successful in previou...
research
06/29/2021

Cascade Decoders-Based Autoencoders for Image Reconstruction

Autoencoders are composed of coding and decoding units, hence they hold ...
research
01/15/2023

EvoAAA: An evolutionary methodology for automated autoencoder architecture search

Machine learning models work better when curated features are provided t...
research
12/03/2020

Lookahead optimizer improves the performance of Convolutional Autoencoders for reconstruction of natural images

Autoencoders are a class of artificial neural networks which have gained...

Please sign up or login with your details

Forgot password? Click here to reset