Publication Details
Comparison of Parallel Linear Genetic Programming Implementations
Linear genetic programming, parallel implementation, island model, hash function, symbolic regresion
Linear genetic programming (LGP) represents candidate programs as sequences of instructions for a register machine. In order to accelerate the evaluation time of candidate programs and reduce the overall time of evolution, we propose parallel implementations of LGP suitable for current multi-core processors. The implementations are based on a parallel evaluation of candidate programs and the island model of parallel evolutionary algorithm in which subpopulations are evolved independently, but some genetic material can be exchanged by means of migration. Proposed implementations are evaluated using three symbolic regression problems and hash function design problem.
@INPROCEEDINGS{FITPUB10997, author = "David Grochol and Luk\'{a}\v{s} Sekanina", title = "Comparison of Parallel Linear Genetic Programming Implementations", pages = "64--76", booktitle = "Recent Advances in Soft Computing: Proceedings of the 22nd International Conference on Soft Computing (MENDEL 2016) held in Brno, Czech Republic, at June 8-10, 2016", year = 2017, location = "Cham, DE", publisher = "Springer International Publishing", ISBN = "978-3-319-58088-3", doi = "10.1007/978-3-319-58088-3\_7", language = "english", url = "https://www.fit.vut.cz/research/publication/10997" }