Computer Science @ University of St Andrews

University of St Andrews crest

Dr Mike Weir

Dr Mike Weir

Position: Lecturer

Research profile

Email (@st-andrews.ac.uk): mkw

Office: JC1.25 - Jack Cole Building, North Haugh

Phone: +44 (0)1334 46 3255

Home page: https://mkw.host.cs.st-andrews.ac.uk

Research Overview

Current research is with the Intelligent Computation Group at the University of St Andrews.


Why are people still smarter than digital computers? A serial digital computer can perform millions of operations per second, while the human brain has a firing cycle for each neuron of the order of milliseconds. One conclusion from these facts is that the human brain's superior abilities are made possible through massive parallel distributed processing and representation. The incorporation of such parallelism into artificial systems with semi-conductor switching speeds offers the potential of very powerful capabilities. For the capabilities to be realised as actual abilities though, the parallelism has to be organised appropriately. Artificial neural networks are an attempt to provide systems incorporating these features effectively by modelling abstract computational features of the brain's information processing.


The aim of the Intelligent Computation Group at St Andrews is to provide such effective computation through modelling of both biological and cognitive insights into intelligent information processing and representation. This modelling also incorporates other artificial intelligence techniques such as Symbolic AI and Artificial Life into neural systems where they are appropriate. Heuristic search is used to provide benchmarks for the effectiveness of the computation.

Recent Publications

High Quality Goal Connection For Nonholonomic Obstacle Navigation Allowing For Drift Using Dynamic Potential Fields

Weir, MK & Bott, MP 2010, High Quality Goal Connection For Nonholonomic Obstacle Navigation Allowing For Drift Using Dynamic Potential Fields. in 2010 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 3221-3226, 2010 IEEE International Conference on Robotics and Automation, ICRA 2010, Anchorage, United States, 3-7 May. DOI: 10.1109/ROBOT.2010.5509519

Enabling nonholonomic smoothness generically allowing for unpredictable drift

Weir, MK, Lewis, JP & Bott, MP 2008, Enabling nonholonomic smoothness generically allowing for unpredictable drift. in 10th International Conference on Control, Automation, Robotics and Vision, 2008. ICARCV 2008. IEEE, pp. 2072-2077, 2008 10th International Conference on Control, Automation, Robotics and Vision, ICARCV 2008, Hanoi, Viet Nam, 17-20 December. DOI: 10.1109/ICARCV.2008.4795850

POTBUG: A mind's eye approach to providing BUG-like guarantees for adaptive obstacle navigation using dynamic potential fields

Weir, M, Buck, A & Lewis, J 2006, POTBUG: A mind's eye approach to providing BUG-like guarantees for adaptive obstacle navigation using dynamic potential fields. in S Nolfi, G Baldassarre, R Calabretta, JCT Hallam, D Marocco, JA Meyer, O Miglino & O Parisi (eds), From Animals to Animats 9: 9th International Conference on Simulation of Adaptive Behaviour. Lecture Notes in Computer Science, vol. 4095, Springer-Verlag, pp. 239-250, 9th International Conference on Simulation of Adaptive Behaviour, SAB 2006, Rome, Italy, 25-29 September. DOI: 10.1007/11840541_20

Agent Navigation Using Potential Fields and Forward Chaining

Forward Chaining for Robot and Agent Navigation using Potential Fields

An Approach to Guaranteeing Generalisation in Neural Networks

Neural Steering: Difficult and Impossible Sequential Problems for Gradient Descent

Using Tangent Hyperplanes to Direct Neural Training

Weir, MK, Lewis, JP, Milligan, G, Bothe, H & Rojas, R 2000, 'Using Tangent Hyperplanes to Direct Neural Training'.

Improving Generalisation Using Neural Bi-Directional Convergence

Subgoal Chaining and the Local Minimum Problem