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. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/TNNLS.2011.2177860 | IEEE Trans. Neural Netw. Learning Syst. |
Keywords | DocType | Volume |
sensitivity,benefit principle,adaptive learning algorithm,learning rule,madaline rule ii,learning (artificial intelligence),backpropagation algorithm,benchmark data,bfnn weight variation,bfnn learning,adaptive learning principles,binary feedforward neural network,feedforward neural nets,sensitivity measurement,binary feedforward neural networks,sbalr algorithm,sensitivity-based adaptive learning rules,minimal disturbance principle,learning control rule,weight adaptation rule,neuron selection rule,burden-sharing principle,sensitivity analysis,neural network,adaptive learning,feedforward neural network | Journal | 23 |
Issue | ISSN | Citations |
3 | 2162-2388 | 7 |
PageRank | References | Authors |
0.57 | 10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuiming Zhong | 1 | 79 | 7.30 |
Xiaoqin Zeng | 2 | 407 | 32.97 |
Shengli Wu | 3 | 370 | 33.55 |
Lixin Han | 4 | 135 | 14.47 |