Running Genetic Programming Backwards Export

@incollection{citeulike:2837426, abstract = {Backward chaining evolutionary algorithms (BC-EA) offer the prospect of run-time efficiency savings by reducing the number of fitness evaluations without significantly changing the course of genetic algorithm or genetic programming runs. ” Tournament selection, iterated coupon-collection problem, and backward-chaining evolutionary algorithm,” Poli, FOGA, 2005 describes how BC-EA does this by avoiding the generation and evaluation of individuals which never appear in selection tournaments. It suggests the largest savings occur in very large populations, short runs, small tournament sizes and shows actual savings in fixed-length binary GAS. Here, we provide a generational GP implementation, including mutation and two offspring crossover of BC-EA and empirically investigate its efficiency in terms of both fitness evaluations and effectiveness.}, author = {Poli, Riccardo and Langdon, William}, citeulike-article-id = {2837426}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/0-387-28111-8_9}, doi = {10.1007/0-387-28111-8_9}, journal = {Genetic Programming Theory and Practice III}, keywords = {06, bc-ea}, pages = {125--140}, posted-at = {2008-11-10 15:56:59}, priority = {2}, title = {Running Genetic Programming Backwards}, url = {http://dx.doi.org/10.1007/0-387-28111-8_9}, year = {2006} }

TY - CHAP ID - citeulike:2837426 L3 - citeulike-article-id:2837426 N2 - Backward chaining evolutionary algorithms (BC-EA) offer the prospect of run-time efficiency savings by reducing the number of fitness evaluations without significantly changing the course of genetic algorithm or genetic programming runs. “Tournament selection, iterated coupon-collection problem, and backward-chaining evolutionary algorithm,” Poli, FOGA, 2005 describes how BC-EA does this by avoiding the generation and evaluation of individuals which never appear in selection tournaments. It suggests the largest savings occur in very large populations, short runs, small tournament sizes and shows actual savings in fixed-length binary GAS. Here, we provide a generational GP implementation, including mutation and two offspring crossover of BC-EA and empirically investigate its efficiency in terms of both fitness evaluations and effectiveness. JF - Genetic Programming Theory and Practice III EP - 140 TI - Running Genetic Programming Backwards SP - 125 KW - 06 KW - bc-ea AU - Poli, Riccardo AU - Langdon, William PY - 2006/// UR - http://dx.doi.org/10.1007/0-387-28111-8_9 ER -