The University of Southampton
University of Southampton Institutional Repository

Two novel Performance improvements for evolving CNN topologies

Two novel Performance improvements for evolving CNN topologies
Two novel Performance improvements for evolving CNN topologies
Convolutional Neural Networks (CNNs) are the state-of-the-art algorithms for the processing of images. However the configuration and training of these networks is a complex task requiring deep domain knowledge, experience and much trial and error. Using genetic algorithms, competitive CNN topologies for image recognition can be produced for any specific purpose, however in previous work this has come at high computational cost. In this work two novel approaches are presented to the utilisation of these algorithms, effective in reducing complexity and training time by nearly 20%. This is accomplished via regularisation directly on training time, and the use of partial training to enable early ranking of individual architectures. Both approaches are validated on the benchmark CIFAR10 data set, and maintain accuracy.
Computer Vision, Genetic Algorithm
Strauch, Yaron Leander
a246b519-5a8a-4011-b330-7184abc055eb
Grundy, Jo
0bc72187-8dce-41fc-b809-93a6adbe0980
Strauch, Yaron Leander
a246b519-5a8a-4011-b330-7184abc055eb
Grundy, Jo
0bc72187-8dce-41fc-b809-93a6adbe0980

Strauch, Yaron Leander and Grundy, Jo (2021) Two novel Performance improvements for evolving CNN topologies. Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), Online, Vancouver, Canada. 02 - 09 Feb 2021. 5 pp .

Record type: Conference or Workshop Item (Paper)

Abstract

Convolutional Neural Networks (CNNs) are the state-of-the-art algorithms for the processing of images. However the configuration and training of these networks is a complex task requiring deep domain knowledge, experience and much trial and error. Using genetic algorithms, competitive CNN topologies for image recognition can be produced for any specific purpose, however in previous work this has come at high computational cost. In this work two novel approaches are presented to the utilisation of these algorithms, effective in reducing complexity and training time by nearly 20%. This is accomplished via regularisation directly on training time, and the use of partial training to enable early ranking of individual architectures. Both approaches are validated on the benchmark CIFAR10 data set, and maintain accuracy.

This record has no associated files available for download.

More information

Published date: 10 February 2021
Venue - Dates: Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), Online, Vancouver, Canada, 2021-02-02 - 2021-02-09
Keywords: Computer Vision, Genetic Algorithm

Identifiers

Local EPrints ID: 446487
URI: http://eprints.soton.ac.uk/id/eprint/446487
PURE UUID: 773bc97a-99d0-4d3e-abf0-63f4c4cc5cf7
ORCID for Yaron Leander Strauch: ORCID iD orcid.org/0000-0003-0820-8319
ORCID for Jo Grundy: ORCID iD orcid.org/0000-0003-2583-5680

Catalogue record

Date deposited: 11 Feb 2021 17:33
Last modified: 17 Mar 2024 03:55

Export record

Contributors

Author: Yaron Leander Strauch ORCID iD
Author: Jo Grundy ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×