On-line evolutionary learning of NN-MLP based on the attentional learning concept
Qiangfu Zhao · 2002
To design the nearest neighbor based multilayer perceptron (NN-MLP) efficiently, the author has proposed a new evolutionary learning algorithm called the R/sup 4/-rule. For off-line learning, the R/sup 4/-rule can produce the smallest or nearly smallest networks with high generalization ability by iteratively performing four basic operations: recognition, remembrance, reduction and review. To apply the algorithm to on-line evolutionary learning of NN-MLP, this paper proposes some improvements for the R/sup 4/-rule based on the attentional learning concept. The performance of the improved algorithm is verified by experimental results.