Previous [ 1] [ 2] [ 3] [ 4] [ 5] [ 6] [ 7] [ 8] [ 9] [ 10] [ 11] [ 12] [ 13]


Journal of Information Science and Engineering, Vol. 32 No. 5, pp. 1301-1324 (September 2016)


Hybrid Bat and Levenberg-Marquardt Algorithms for Artificial Neural Networks Learning


NAZRI MOHD NAWI1, MUHAMMAD ZUBAIR REHMAN1, ABDULLAH KHAN1, ARSLAN KIYANI1 HARUNA CHIROMA2 AND TUTUT HERAWAN2
1Software and Multimedia Centre
Faculty of Computer Science and Information Technology
Universiti Tun Hussein Onn Malaysia
Johor, 86400 Malaysia
2Faculty of Computer Science and Information Technology
University of Malaya
Lumpur, 50603 Malaysia
2Universitas Teknologi Yogyakarta
2AMCS Research Center, Yogyakarta, Indonesia
E-mail: nazri@uthm.edu.my

The Levenberg-Marquardt (LM) gradient descent algorithm is used extensively for the training of Artificial Neural Networks (ANN) in the literature, despite its limitations, such as susceptibility to the local minima that undermine its robustness. In this paper, a bio-inspired algorithm referring to the Bat algorithm was proposed for training the ANN, to deviate from the limitations of the LM. The proposed Bat algorithm-based LM (BALM) was simulated on 10 benchmark datasets. For evaluation of the proposed BALM, comparative simulation experiments were conducted. The experimental results indicated that the BALM was found to deviate from the limitations of the LM to advance the accuracy and convergence speed of the ANN. Also, the BALM performs better than the back-propagation algorithm, artificial bee colony trained back-propagation ANN, and artificial bee colony trained LM ANN. The results of this research provide an alternative ANN training algorithm that can be used by researchers and industries to solve complex real-world problems across numerous domains of applications.

Keywords: bat algorithm, Levenberg-Marquardt algorithm, artificial neural networks, optimization, swarm intelligence

Full Text () Retrieve PDF document (201609_10.pdf)

Received May 24, 2015; revised July 17, 2015; accepted August 28, 2015.
Communicated by Jen-Tzung Chien.