Name
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. |
Year | DOI | Venue |
|---|---|---|
1996 | 10.1007/BF00426023 | Neural Processing Letters |
Keywords | Field | DocType |
adaptation,diploidy,genetic algorithms,genotype-phenotype mapping,neural networks | Genotype,Population,Ploidy,Gene,Mutation rate,Artificial intelligence,Artificial neural network,Evolutionary biology,Genetic algorithm,Machine learning,Mathematics | Journal |
Volume | Issue | ISSN |
4 | 3 | 1370-4621 |
Citations | PageRank | References |
8 | 0.60 | 2 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Raffaele Calabretta | 1 | 89 | 12.94 |
| Riccardo Galbiati | 2 | 8 | 0.60 |
| Stefano Nolfi | 3 | 2118 | 192.54 |
| Domenico Parisi | 4 | 745 | 101.62 |