Back to Search
Start Over
Accelerating Real-Valued Genetic Algorithms Using Mutation-with-Momentum.
- Source :
- AI 2005: Advances in Artificial Intelligence; 2005, p1108-1111, 4p
- Publication Year :
- 2005
-
Abstract
- Directed mutation has been proposed for improving the convergence speed of GAs on problems involving real-valued alleles. This paper proposes a directed mutation approach based on the momentum term used in gradient descent training of neural networks. Mutation-with-momentum is compared against gaussian mutation and is shown to regularly result in improvements in performance during early generations. A hybrid of momentum and gaussian mutation is shown to outperform either individual approach to mutation. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISBNs :
- 9783540304623
- Database :
- Supplemental Index
- Journal :
- AI 2005: Advances in Artificial Intelligence
- Publication Type :
- Book
- Accession number :
- 32884539
- Full Text :
- https://doi.org/10.1007/11589990_149