In 2010, I graduated from the University of York with a First class MEng degree in Computer Systems and Software Engineering, and in 2014 with a PhD in Computer Science. For two years I worked as a Research Associate at York, with a focus on automated program improvement using hyper-heuristic genetic programming, and automated testing of multicore embedded systems.

During my PhD I completed the 'Preparing Future Academics' course, and did quite a lot of undergraduate teaching - ranging from programming languages and algorithms, to computer graphics and real-time systems. The focus of my thesis was the use of simple neural networks to efficiently solve computationally difficult problems.

I am now a Software Engineer at IBM, although I am still actively collaborating on research with members of the Non-Standard Computation group in the Computer Science department of the University of York.

My CV is available here:

Erdös-Bacon: 8

Improving the Associative Rule Chaining Architecture


DOI: 10.1007/978-3-642-40728-4_13
Authors: Nathan Burles, Simon O'Keefe, James Austin

Published in Artificial Neural Networks and Machine Learning – ICANN 2013.

Attached is a draft copy.

ICANN2013 timeframe:

Submission deadline: 2013-03-15
Acceptance: 2013-05-18
​Camera-ready: 2013-05-31

Extending the Associative Rule Chaining Architecture for Multiple Arity Rules


Authors: Nathan Burles, James Austin, Simon O'Keefe

Published in the Neural-Symbolic Learning and Reasoning workshop 2013 proceedings, available at

Attached is a draft copy.

NeSy13 timeframe:

Submission deadline: 2013-03-22
Acceptance: 2013-05-21
Camera-ready: 2013-05-27

A Rule Chaining Architecture Using a Correlation Matrix Memory


DOI: 10.1007/978-3-642-33269-2_7
Authors: James Austin, Stephen Hobson, Nathan Burles, Simon O'Keefe

Published in Artificial Neural Networks and Machine Learning – ICANN 2012.

Attached is a draft copy.

ICANN2012 timeframe:

Submission deadline: 2012-04-09
Acceptance: 2012-06-24
Camera-ready: 2012-07-01


Subscribe to RSS - Academic