Designing Neural Networks Using PSO-Based Memetic Algorithm

by: Bo Liu, Ling Wang, Yihui Jin, Dexian Huang

Advances in Neural Networks – ISNN 2007 (2007), pp. 219-224.

View FullText article

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

zzztimbo, mahmoodr

Find related articles with these CiteULike tags

07, 2s, fixed-structure, memetic-algorithm, meta-lamarckian-learning, neural-network, nn, no-tag, particle-swarm-optimization, pso

Abstract

This paper proposes an effective particle swarm optimization (PSO) based memetic algorithm (MA) for designing artificial neural network. In the proposed PSO-based MA (PSOMA), not only the evolutionary searching mechanism of PSO characterized by individual improvement plus population cooperation and competition is applied to perform the global search, but also several adaptive high-performance faster training algorithms are employed to enhance the local search, so that the exploration and exploitation abilities of PSOMA can be well balanced. Moreover, an effective adaptive Meta-Lamarckian learning strategy is employed to decide which local search method to be used so as to prevent the premature convergence and concentrate computing effort on promising neighbor solutions. Simulation results and comparisons demonstrate the effectiveness and efficiency of the proposed PSOMA.

@incollection{citeulike:2181622, abstract = {This paper proposes an effective particle swarm optimization (PSO) based memetic algorithm (MA) for designing artificial neural network. In the proposed PSO-based MA (PSOMA), not only the evolutionary searching mechanism of PSO characterized by individual improvement plus population cooperation and competition is applied to perform the global search, but also several adaptive high-performance faster training algorithms are employed to enhance the local search, so that the exploration and exploitation abilities of PSOMA can be well balanced. Moreover, an effective adaptive Meta-Lamarckian learning strategy is employed to decide which local search method to be used so as to prevent the premature convergence and concentrate computing effort on promising neighbor solutions. Simulation results and comparisons demonstrate the effectiveness and efficiency of the proposed PSOMA.}, author = {Liu, Bo and Wang, Ling and Jin, Yihui and Huang, Dexian }, citeulike-article-id = {2181622}, doi = {10.1007/978-3-540-72395-0\_28}, journal = {Advances in Neural Networks – ISNN 2007}, pages = {219--224}, posted-at = {2008-03-21 13:05:16}, priority = {2}, title = {Designing Neural Networks Using PSO-Based Memetic Algorithm}, url = {http://dx.doi.org/10.1007/978-3-540-72395-0\_28}, year = {2007} }

RIS record

TY - CHAP ID - citeulike:2181622 L3 - citeulike-article-id:2181622 TI - Designing Neural Networks Using PSO-Based Memetic Algorithm JF - Advances in Neural Networks – ISNN 2007 SP - 219 EP - 224 N2 - This paper proposes an effective particle swarm optimization (PSO) based memetic algorithm (MA) for designing artificial neural network. In the proposed PSO-based MA (PSOMA), not only the evolutionary searching mechanism of PSO characterized by individual improvement plus population cooperation and competition is applied to perform the global search, but also several adaptive high-performance faster training algorithms are employed to enhance the local search, so that the exploration and exploitation abilities of PSOMA can be well balanced. Moreover, an effective adaptive Meta-Lamarckian learning strategy is employed to decide which local search method to be used so as to prevent the premature convergence and concentrate computing effort on promising neighbor solutions. Simulation results and comparisons demonstrate the effectiveness and efficiency of the proposed PSOMA. AU - Liu, Bo AU - Wang, Ling AU - Jin, Yihui AU - Huang, Dexian PY - 2007/// UR - http://dx.doi.org/10.1007/978-3-540-72395-0_28 ER -

RIS BibTeX