Towards optimisers that `Keep Learning'

Research Output

We consider optimisation in the context of the need to apply an optimiser to a continual stream of instances from one or more domains, and consider how such a system might 'keep learning': by drawing on past experience to improve performance and learning how to both predict and react to instance and/or domain drift.

Date:

24 July 2023
Publication Status:

Published
Publisher

ACM
DOI:

10.1145/3583133.3596344
Funders:

Engineering and Physical Sciences Research Council

http://researchrepository.napier.ac.uk/output/3156082 <p>Hart, E., Miguel, I., Stone, C., & Renau, Q. (2023, July). <i>Towards optimisers that `Keep Learning'</i>. Presented at Companion Conference on Genetic and Evolutionary Computation, Lisbon, Portugal</p>

Citation

Hart, E., Miguel, I., Stone, C., & Renau, Q. (2023, July). Towards optimisers that `Keep Learning'. Presented at Companion Conference on Genetic and Evolutionary Computation, Lisbon, Portugal