IIS + CAIR = APPLIED REPRESENTATION LEARNING LAB

The Applied Representation Learning Lab as part of The Institute for Intelligent Systems (IIS) is now a research group node under Centre for Artificial Intelligence Research (CAIR)

CATASTROPHIC FORGETTING IN SIMILARITY LEARNING

This research project looks at the impact of catastrophic forgetting and incremental learning in similarity learning.

CATASTROPHIC FORGETTING IN SIMILARITY LEARNING

Representation Learning

The recent paper by Variawa and van Zyl inter al. (2022) [ref] looks at transfer learning and deep metric learning for galaxy morphology classification. The most exciting result from this paper is that metric learning outperformed traditional classification on the minority classes. Prevalence of minority classes seems to be a characteristic of crowdsourced data, a red flag raised in this study and requiring consideration in similar projects.

MACHINE LEARNING IN FINANCE

This research project looks at the intersection of finance and machine learning.

SURROGATE ASSISTED AGENT BASED MODELLING

Agent-Based Models (ABMs) as complex adaptive simulations which are able to incorporate real world nuance into their design. This research looks at the surrogate (machine learning) assisted agent based modelling.

SURROGATE ASSISTED DATA-DRIVEN EVOLUTIONARY COMPUTING

Interesting applications arises at the intersection of evolutionary computing and machine learning when we capitalise on the strengths of both of these paradigms simultaneously.

NEDBANK RESEARCH CHAIR

I currently hold the Nedbank Research and Innovation Chair. The Chair is housed at the University of Johannesburg’s Institute for Intelligent systems.