Title | ||
---|---|---|
A Genetic Algorithm with Adaptive Mutations and Family Competition for Training Neural Networks |
Abstract | ||
---|---|---|
In this paper, we present a new evolutionary technique to train three general neural networks. Based on family competition principles and adaptive rules, the proposed approach integrates decreasing-based mutations and self-adaptive mutations to collaborate with each other. Dierent mutations act as global and local strategies respectively to balance the trade-o between solution quality and convergence speed. Our algorithm is then applied to three dierent task domains: Boolean functions, regular language recognition, and articial ant problems. Experimental results indicate that the proposed algorithm is very competitive with comparable evolutionary algorithms. We also discuss the search power of our proposed approach. |
Year | DOI | Venue |
---|---|---|
2000 | 10.1142/S0129065700000314 | Int. J. Neural Syst. |
Field | DocType | Volume |
Boolean function,Convergence (routing),Evolutionary algorithm,Computer science,Artificial intelligence,Regular language,Artificial neural network,Genetic algorithm,Machine learning | Journal | 10 |
Issue | Citations | PageRank |
5 | 5 | 0.64 |
References | Authors | |
24 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jinn-moon Yang | 1 | 364 | 35.89 |
Jorng-Tzong Horng | 2 | 541 | 67.78 |
Cheng-yan Kao | 3 | 586 | 61.50 |