Volume 3, Issue 2 (3-2015)                   SCJ 2015, 3(2): 2-19 | Back to browse issues page

XML Persian Abstract Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Sheikhan M, Abbasnejad Arabi M. Joint Optimization of Structure and Parameters of Neural Networks Using Hybrid Gravitational Search Algorithms in Classification and Function Approximation Tasks. SCJ. 2015; 3 (2) :2-19
URL: http://scj.kashanu.ac.ir/article-1-161-en.html
1- , msheikhn@azad.ac.ir
Abstract:   (4142 Views)
Determining the optimum number of nodes, number of hidden layers, and synaptic connection weights in an artificial neural network (ANN) plays an important role in the performance of this soft computing model. Several methods have been proposed for weights update (training) and structure selection of the ANNs. For example, the error back-propagation (EBP) is a traditional method for weights update of multi-layer networks. In this study, gravitational search algorithm (GSA), as a modern swarm intelligence optimization method, is used for this purpose. In this way, GSA and its binary version (BGSA) are used concurrently, as a hybrid method, to optimize the weights and number of hidden-layer nodes of an ANN, respectively. The performance of proposed method is compared with other intelligent and traditional methods such as particle swarm optimization (PSO), PSO-BPSO hybrid, and EBP in classification and function approximation tasks. The performance is evaluated over Iris, Breast Cancer, and Glass datasets for classification. For function approximation task, the performance is evaluated for a prosody predictor that is used for natural speech synthesis. To reduce the number of inputs to prosody predictor, a hybrid of an genetic algorithm and ant colony optimization algorithm is used for feature selection.  Simulation results show that the proposed method can offer competitive classification and prediction accuracies while using a reduced number of hidden neurons (25-68 percent reduction) as compared to other investigated algorithms.    
Full-Text [PDF 986 kb]   (3840 Downloads)    
Type of Study: Research | Subject: Special
Received: 2014/06/25 | Accepted: 2014/12/7 | Published: 2015/09/3

Add your comments about this article : Your username or Email:

Send email to the article author

© 2020 All Rights Reserved | Soft Computing Journal

Designed & Developed by : Yektaweb