Artificial neural network training utilizing the smooth variable structure filter estimation strategy. Issue 3 (April 2016)

• Record Type: Journal Article
• Authors: Ahmed, Ryan; El Sayed, Mohammed; Gadsden, S.; Tjong, Jimi; Habibi, Saeid
• Is Part Of: Neural computing & applications. Volume 27:Issue 3(2016)
• Page Start: 537
• Page End: 548
• Publication Date: 2016-04
• Subjects: Neural networks -- Extended Kalman filter -- Smooth variable structure filter -- Estimation; Neural networks (Computer science) -- Periodicals; Neural circuitry -- Periodicals; Artificial intelligence -- Periodicals; Neural Networks (Computer) -- Periodicals; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux nerveux -- Périodiques; Intelligence artificielle -- Périodiques; 006.32
• DOI: 10.1007/s00521-015-1875-2
• Languages: English
• ISSNs: 0941-0643

Abstract

Abstract A multilayered neural network is a multi-input, multi-output nonlinear system in which network weights can be trained by using parameter estimation algorithms. In this paper, a novel training method is proposed. This method is based on the relatively new smooth variable structure filter (SVSF) and is formulated for feed-forward multilayer perceptron training. The SVSF is a state and parameter estimation that is based on the sliding mode concept and works in a predictor–corrector fashion. The SVSF training performance is tested on three benchmark pattern classification problems. Furthermore, a study is presented comparing the popular back-propagation method, the extended Kalman filter, and the SVSF.