Ulster University Logo

Ulster Institutional Repository

Sensitivity-Based Adaptive Learning Rules for Binary Feedforward Neural Networks

Biomedical Sciences Research Institute Computer Science Research Institute Environmental Sciences Research Institute Nanotechnology & Advanced Materials Research Institute

Zhong, Shuiming, Zeng, Xiaoqin, Wu, Shengli and Han, Lixin (2012) Sensitivity-Based Adaptive Learning Rules for Binary Feedforward Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 23 (3). pp. 480-491. [Journal article]

Full text not available from this repository.

URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6134678

DOI: 10.1109/TNNLS.2011.2177860

Abstract

This paper proposes a set of adaptive learning rules for binary feedforward neural networks (BFNNs) by means of the sensitivity measure that is established to investigate the effect of a BFNN's weight variation on its output. The rules are based on three basic adaptive learning principles: the benefit principle, the minimal disturbance principle, and the burden-sharing principle. In order to follow the benefit principle and the minimal disturbance principle, a neuron selection rule and a weight adaptation rule are developed. Besides, a learning control rule is developed to follow the burden-sharing principle. The advantage of the rules is that they can effectively guide the BFNN's learning to conduct constructive adaptations and avoid destructive ones. With these rules, a sensitivity-based adaptive learning (SBALR) algorithm for BFNNs is presented. Experimental results on a number of benchmark data demonstrate that the SBALR algorithm has better learning performance than the Madaline rule II and backpropagation algorithms.

Item Type:Journal article
Faculties and Schools:Faculty of Computing & Engineering
Faculty of Computing & Engineering > School of Computing and Mathematics
Research Institutes and Groups:Computer Science Research Institute
Computer Science Research Institute > Artificial Intelligence and Applications
ID Code:22969
Deposited By:Dr Shengli Wu
Deposited On:13 Aug 2012 12:33
Last Modified:13 Aug 2012 12:33

Repository Staff Only: item control page