Metalearning in Optimisation and Machine Learning скачать в хорошем качестве

Metalearning in Optimisation and Machine Learning

Speaker: Katherine Malan (University of South Africa) Title: Metalearning in Optimisation and Machine Learning Summary: In this talk, I will focus on metalearning in the context of computational intelligence (CI) solutions to problems. I will show how the phenomenon called “performance complementarity” is prevalent in different CI domains and how data-driven analysis on the performance of CI approaches on different problem types can be used as the basis for automated algorithm/model selection. Examples will include constraint handling for evolutionary algorithms, feature selection for data mining, time series forecasting, approaches to regularisation in deep neural networks, and topic modelling algorithms for large language models. Biography: Katherine Malan is a professor in the Department of Decision Sciences, University of South Africa. She received her PhD in Computer Science from the University of Pretoria in 2014. She has 30 years’ lecturing experience, mostly in Computer Science, at three different South African universities and has co-authored two programming textbooks. She is editor-in-chief of South African Computer Journal, associate editor for Engineering Applications of Artificial Intelligence, previous co-chair of the ENUM track of GECCO, and has served as a reviewer for over 20 Web of Science journals. Her research interests include automated algorithm/model selection in optimisation and machine learning and search landscape analysis and the link to optimisation algorithm performance.