Parallel Differential Evolution Algorithm with Multiple Trial Vectors to Artificial Neural Network Training

dc.contributor.author	Thein, Htet Thazin Tike
dc.contributor.author	Tun, Khin Mo Mo
dc.date.accessioned	2019-07-02T06:41:00Z
dc.date.available	2019-07-02T06:41:00Z
dc.date.issued	2015-02-05
dc.identifier.uri	http://onlineresource.ucsy.edu.mm/handle/123456789/63
dc.description.abstract	In this paper, parallel differential evolution algorithm with multiple trial vectors for training artificial neural networks (ANNs) is presented. The proposed method is PDEA, which is a DE-ANN+ modified by adding island model. Within PDEA, an island model is designed to cooperatively search for the global optima in search space. By combining the strengths of the differential evolution algorithm with multiple trial vectors and island model, PDEA greatly improves the optimization performance. PDEA algorithm is used for ANN training to classify the parity-p problem. Results obtained using proposed algorithm has been compared to the results obtained using other evolutionary algorithms.	en_US
dc.language.iso	en	en_US
dc.publisher	Thirteenth International Conferences on Computer Applications(ICCA 2015)	en_US
dc.subject	Artificial Intelligence	en_US
dc.subject	artificial neural network	en_US
dc.subject	differential evolution algorithm	en_US
dc.subject	multiple and trial vectors	en_US
dc.subject	training method	en_US
dc.subject	island model	en_US
dc.title	Parallel Differential Evolution Algorithm with Multiple Trial Vectors to Artificial Neural Network Training	en_US
dc.type	Article	en_US