In this paper, we propose a novel associative chaotic neural network (NACNN) via exponential decay effect. We replace historic spatio-temporal effect on neural network with new exponential decay parameters, which is more close to the facts. As we know, historic effect on our memory always decreases at exponential level with the time increasing. The proposed model can realize one-to-many associations perfectly. The effectiveness of our scheme is illustrated by a series of computer simulations.
展开▼
