Minimising Testing in Genetic Programming
Department of Computer Science, University College London, Gower Street, London WC1E 6BT, UK
University College London, Technical report RN/11/10, 2011
The cost of optimisation can be reduced by evaluating candidate designs on only a fraction of all possible use cases. We show how genetic programming (GP) can avoid overfitting and evolve general solutions from fitness test suites as small as just one dynamic training case. Search effort can be greatly reduced.
December 15, 2011 by hgpu
