An Analysis of Current Continual Learning Algorithms in an Image Classification Context

Jess Wakelin*, Noor Mohammedali

*Corresponding author for this work

Research output: Contribution to Book/ReportConference Contributionpeer-review

Abstract

Artificial Intelligence aims to mimic natural intelligent learning by using lifelong-machine-learning, which allows an AI to train and learn over it's lifetime. Various algorithms have been suggested and developed to allow lifelong learning, these algorithms require deeper analysis, to evaluate and highlight performance benefits. In this research, we will study with three state-of-the-art algorithms for lifelong learning: Rehearsal, elastic-weight-consolidation and synaptic-intelligence. We do an analysis and evaluation of their performance in a multiple task experiment, using different amounts of data, measuring several performance metrics. We found that these algorithms are similar in performance, but some algorithms perform better than others with less data, or show good performance in task one, but not subsequent tasks. These algorithms could be built upon and improved in future research. The evaluation demonstrated in this research are in the image classification context.
Original languageEnglish
Title of host publicationInternational Symposium on Computer Science and Intelligent Control
PublisherIEEE Computer Society's Conference Publishing Services (CPS)
Pages1-6
Number of pages6
Publication statusAccepted/In press - 25 Oct 2022
EventThe 6th International Symposium on Computer Science and Intelligent Control - Beijing, China
Duration: 11 Nov 202213 Nov 2022
Conference number: 6
https://www.iscsic.org/

Conference

ConferenceThe 6th International Symposium on Computer Science and Intelligent Control
Abbreviated titleISCSIC 2022
Country/TerritoryChina
CityBeijing
Period11/11/2213/11/22
Internet address

Keywords

  • Continuous Learning
  • Image Classification
  • Lifelong Machine Learning
  • Non-Continuous Learning
  • Machine Learning
  • Artificial Intelligence
  • Intelligent Agent

Fingerprint

Dive into the research topics of 'An Analysis of Current Continual Learning Algorithms in an Image Classification Context'. Together they form a unique fingerprint.

Cite this