Learning Cognitive Systems: evolving symbolic rules containing neuro identified features

Speaker

Prof. Will Browne, Chair in Manufacturing Robotics at Queensland University of Technology

Abstract

The learning in Neurosymbolic systems is often based on Connectionist principals, however the alternative 'AI tribe' of Evolutionary Computation (EC) can also be used. This talk describes how EC can learn 'if then' rules that link symbols to features from the environment. These features can be captured utilising connectionist approaches. EC excels at finding higher-order/abstract patterns, but gets swamped at the pixel level. Whereas connectionist approaches are great at finding meta-features at the pixel level, but struggle to find higher-order/abstract patterns. Combining both offers a pathway to learning cognitive systems.

Bio

Prof. Will Browne's research focuses on applied cognitive systems. Specifically, how to use inspiration from natural intelligence to enable computers/machines/robots to behave usefully. This includes cognitive robotics, learning classifier systems, and modern heuristics for industrial application. Prof. Browne is an experienced co-track chair for the Genetics-Based Machine Learning (GBML) track and the co-chair for the Evolutionary Machine Learning track at the Genetic and Evolutionary Computation Conference. He has also provided tutorials on Rule-Based Machine Learning and Advanced Learning Classifier Systems at GECCO, chaired the International Workshop on Learning Classifier Systems (LCSs), and lectured graduate courses on LCSs. He has co-authored the first textbook on LCSs Introduction to Learning Classifier Systems, Springer 2017. Currently, he is Professor and Chair in Manufacturing Robotics at Queensland University of Technology, Brisbane, Queensland, Australia.