AN IMPROVED CONTROLLED CHAOTIC NEURAL NETWORK FOR PATTERN RECOGNITION

A sigmoid function is necessary for creation a chaotic neural network (CNN). In this paper, a new function for CNN is proposed that it can increase the speed of convergence. In the proposed method, we use a novel signal for controlling chaos. Both the theory analysis and computer simulation results show that the performance of CNN can be improved remarkably by using our method. By means of this control method, the outputs of the controlled CNN converge to the stored patterns and they are dependent on the initial patterns. We observed that the controlled CNN can distinguish two initial patterns even if they are slightly different. These characteristics imply that the controlled CNN can be used for pattern recognition.