Tuesday, 25 October 2016

Cognitive Learning using Evolutionary Computation

Cognitive Learning using Evolutionary Computation

Associate Professor Will Browne
Victoria University, New Zealand

28 October at 13.30
Ron Cooke Hub, Heslington East - RCH/204

Abstract

Artificial Cognitive Systems encompasses machine intelligence systems, such as robots, that interact with their environment. 

This talk will highlight research that enables such systems to learn and adapt to problems in their domain and in
related domains. 

The symbolic evolutionary computation technique of LearningClassifier Systems (LCSs) was conceived 40 years ago as an artificial cognitive system. The work presented shows how LCSs can utilise building blocks of
knowledge in heuristics ('if-then' rules) to transfer learnt knowledge from small to large scale problems in the same domain. Furthermore, the use of these rules enables functionality learned in sub-problems to be transferred to related problems. 

Results show that provided the human experimenter can set a rough curriculum for learning concepts, the underlying patterns/models in a problem domain can be learnt in an interpretable manner.


An interdisciplinary seminar series aimed at researchers from all disciplines
The seminar is followed by a refreshment break prior to interdisciplinary discussion 
Hosted by the York Centre for Complex Systems Analysis 

Ron Cooke Hub is on Heslington East Campus – accessible by free bus services Nos. 66 and 44 running at frequent intervals from Heslington West.  The YCCSA Seminar room RCH/204 is on the second floor

No comments:

Post a Comment