Weight Optimization in Recurrent Neural Networks with Hybrid Metaheuristic Cuckoo Search Techniques for Data Classification

Nawi, N.M. and Khan, A. and Rehman, M.Z. and Chiroma, H. and Herawan, T. (2015) Weight Optimization in Recurrent Neural Networks with Hybrid Metaheuristic Cuckoo Search Techniques for Data Classification. Mathematical Problems in Engineering, 2015. ISSN 1024-123X, DOI https://doi.org/10.1155/2015/868375.

PDF (Full Text)
NawiNM_(2015).pdf - Published Version

Download (3MB)
Official URL: http://dx.doi.org/10.1155/2015/868375


Recurrent neural network (RNN) has been widely used as a tool in the data classification. This network can be educated with gradient descent back propagation. However, traditional training algorithms have some drawbacks such as slow speed of convergence being not definite to find the global minimum of the error function since gradient descent may get stuck in local minima. As a solution, nature inspired metaheuristic algorithms provide derivative-free solution to optimize complex problems. This paper proposes a new metaheuristic search algorithm called Cuckoo Search (CS) based on Cuckoo bird’s behavior to train Elman recurrent network (ERN) and back propagation Elman recurrent network (BPERN) in achieving fast convergence rate and to avoid local minima problem. The proposed CSERN and CSBPERN algorithms are compared with artificial bee colony using BP algorithm and other hybrid variants algorithms. Specifically, some selected benchmark classification problems are used. The simulation results show that the computational efficiency of ERN and BPERN training process is highly enhanced when coupled with the proposed hybrid method.

Item Type: Article
Funders: Fundamental Research Grant Scheme (FRGS) Vote no. 1236 from MoHE Malaysia, Program Rakan Penyelidikan University of Malaya (PRPUM) Grant Vote no. CG063-2013
Uncontrolled Keywords: Weight Optimization; Neural Networks; Hybrid Metaheuristic Cuckoo Search Techniques; Data Classification
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Computer Science & Information Technology
Depositing User: Ms. Juhaida Abd Rahim
Date Deposited: 19 Jul 2017 08:12
Last Modified: 19 Jul 2017 08:12
URI: http://eprints.um.edu.my/id/eprint/17529

Actions (login required)

View Item View Item