An Improved Transiently Chaotic Neural Network to Maximum Clique Problem

By analyzing the dynamics behavior and parameter distribution of the transiently chaotic neural network, we propose an improved transiently neural network model with new embedded back-end chaotic dynamics for combinatorial optimization problem and test it on the maximum clique problem. With the new embedded back-end chaotic dynamics, the proposed model can get enough chaotic dynamics to do global and local search, which makes the network success in escaping the local minima and converging completely. Moreover the proposed model has unobvious parameter dependence. The simulation on a number of instances has verified the proposed network model.