Two is better than one: A diploid genotype for neural networks |
| |
Authors: | Raffaele Calabretta Riccardo Galbiati Stefano Nolfi Domenico Parisi |
| |
Affiliation: | (1) Institute of Neural Systems and Artificial Life, Institute of Psychology, National Research Council, Wiale Marx 15, 00137 Rome, Italy;(2) Department of Biology, University Tor Vergata, Via della Ricerce scientifica, 00133 Rome, Italy;(3) Centro di Studio per la Chimica del Farmaco, National Research Council, Piazzale A. Moro 5, 00185 Rome, Italy |
| |
Abstract: | In nature the genotype of many organisms exhibits diploidy, i.e., it includes two copies of every gene. In this paper we describe the results of simulations comparing the behavior of haploid and diploid populations of ecological neural networks living in both fixed and changing environments. We show that diploid genotypes create more variability in fitness in the population than haploid genotypes and buffer better environmental change; as a consequence, if one wants to obtain good results for both average and peak fitness in a single population one should choose a diploid population with an appropriate mutation rate. Some results of our simulations parallel biological findings. |
| |
Keywords: | adaptation diploidy genetic algorithms genotype-phenotype mapping neural networks |
本文献已被 SpringerLink 等数据库收录! |
|