A novel chaotic neural network for many-to-many associations and successive learning
Shukai Duan, Guangyuan Liu, Lidan Wang, Yuhui Qiu · 2003
In this paper, we propose a novel successive learning chaotic neural network (NSLCNN). It has two distinctive features: (1) it can deal with many-to-many associations; (2) it can learn unknown pattern successively. As for the first feature, when a stored pattern is given to the network, the network searches around the input pattern by chaos. The proposed model makes use of this property to deal with many-to-many associations. As for the second one, when a different input pattern is given, a different response is received. So it can distinguish unknown patterns from the known patterns and learn the unknown patterns successively. A series of computer simulations show the effectiveness of the proposed model.