Northampton Electronic Collection of Theses and Research

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

Wakelin, J. and Mohammedali, N. (2023) An Analysis of Current Continual Learning Algorithms in an Image Classification Context. In: 6th International Symposium on Computer Science and Intelligent Control :. CHN: IEEE Computer Society's Conference Publishing Services (CPS). pp. 34-39.

[A][B][+][-]
19746:38463
[thumbnail of Wakelin_etal_IEEE_2022_An_Analysis_of_Current_Continual_Learning_Algorithms_in_an_Image_Classification_Context]
Wakelin_etal_IEEE_2022_An_Analysis_of_Current_Continual_Learning_Algorithms_in_an_Image_Classification_Context
Wakelin_etal_IEEE_2022_An_Analysis_of_Current_Continual_Learning_Algorithms_in_an_Image_Classification_Context.pdf - Accepted Version
Available under License ['licenses_description_unspecified' not defined].
Information
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.
Additional Information:
Publisher's notice for accepted manuscript: "© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works."
Uncontrolled Keywords:
Continuous Learning, Image Classification, Lifelong Machine Learning, Non-Continuous Learning, Machine Learning, Artificial Intelligence, Intelligent Agent
Creators:
Wakelin, J. and Mohammedali, N.
Publisher:
IEEE Computer Society's Conference Publishing Services (CPS)
Date:
14 March 2023
Date Type:
Publication
Page Range:
pp. 34-39
Title of Book:
6th International Symposium on Computer Science and Intelligent Control :
Event Title:
The 6th International Symposium on Computer Science and Intelligent Control
Event Dates:
2022-11-11 - 2022-11-13
Place of Publication:
CHN
Number of Pages:
6
Language:
English
DOI:
10.1109/ISCSIC57216.2022.00019
Status:
Published / Disseminated
Refereed:
Yes
Related URLs:
Edit Item