Paul Darwen

Learn More
I hereby declare that this submission is my own work and that, to the best of my knowledge and belief, it contains no material previously published or written by another person nor material which to a substantial extent has been accepted for the award of any other degree or diploma of a university or other institute of higher learning, except where due(More)
This thesis presents an environment for studying RTS computer controled players, a package for using neural networks and a package for coevolution. It then uses all these packages to create a computer player that employes a neural network. iii iv Acknowledgements I would like to thank several people that had an influence on this document: • My supervisor,(More)
A new population-based incremental learning algorithm for conformational searching of molecules is presented. This algorithm is particularly effective at determining, by relatively small number of energy minimizations, global energy minima of large flexible molecules. The algorithm is also able to find a large set of low energy conformations of more rigid(More)
  • 1