Comparisons of the performance on transient chaotic neural network with different output functions
Qian Li, Liang Sun · 2004
Based on the chaotic simulated annealing network used by Chen & Aihara, which has better searching properties than traditional Hopfield-Tank neural network, we proposed other two different output functions and applied all of them to 4 city TSP respectively. We constructed continuous, discrete and continuous-discrete neural networks, introduced a basic principle to initialize parameter. At last, we analyzed the performance of chaotic neural networks with different output functions, which were measured in terms of feasibility, research efficiency, scalability, convergence speed and computing cost.