Approaches to adaptive stochastic search based on the nonextensive Q-distribution
Magoulas, George and Anastasiadis, A.D. (2006) Approaches to adaptive stochastic search based on the nonextensive Q-distribution. International Journal of Bifurcation and Chaos 16 (7), pp. 2081-2091. ISSN 0218-1274.
Abstract
This paper explores the use of the nonextensive q-distribution in the context of adaptive stochastic searching. The proposed approach consists of generating the "probability" of moving from one point of the search space to another through a probability distribution characterized by the q entropic index of the nonextensive entropy. The potential benefits of this technique are investigated by incorporating it in two different adaptive search algorithmic models to create new modifications of the diffusion method and the particle swarm optimizer. The performance of the modified search algorithms is evaluated in a number of nonlinear optimization and neural network training benchmark problems.
Metadata
Item Type: | Article |
---|---|
School: | Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences |
Depositing User: | Sarah Hall |
Date Deposited: | 22 Jun 2021 12:47 |
Last Modified: | 09 Aug 2023 12:51 |
URI: | https://eprints.bbk.ac.uk/id/eprint/44834 |
Statistics
Additional statistics are available via IRStats2.