Lifelong Learning Machines: Towards Developing Optimisation Systems That Continually Learn

Hart, Emma

Abstract

Standard approaches to developing optimisation algorithms tend to involve selecting an algorithm and tuning it to work well on a large set of problem instances from the domain of interest. Once deployed, the algorithm remains static, failing to improve despite being exposed to a wealth of further example instances. Furthermore, if the characteristics of the instances being solved shift over time, the tuned algorithm is likely to perform poorly. To counter this, we propose the lifelong learning optimiser, which (1) autonomously and continually refines its optimisation algorithm(s) so that they improve with experience and (2) generates novel algorithms if performance drops in reaction to unforeseen data.

Citation

Hart, E. (2022). Lifelong Learning Machines: Towards Developing Optimisation Systems That Continually Learn. In A. E. Smith (Ed.), Women in Computational Intelligence: Key Advances and Perspectives on Emerging Topics (187-203). Springer. https://doi.org/10.1007/978-3-030-79092-9_9

• Online Publication Date: Apr 14, 2022
• Publication Date: 2022
• Deposit Date: Feb 22, 2022
• Publisher: Springer
• Pages: 187-203
• Series Title: Women in Engineering and Science
• Series ISSN: 2509-6427
• Book Title: Women in Computational Intelligence: Key Advances and Perspectives on Emerging Topics
• ISBN: 978-3-030-79091-2
• DOI: https://doi.org/10.1007/978-3-030-79092-9_9
• Keywords: Lifelong learning, Optimisation, Artificial immune systems
• Public URL: http://researchrepository.napier.ac.uk/Output/2846706