Through adding a nonlinear self-feedback term in the evolution equations of
neural network, we introduced a transiently chaotic neural network model.
In order to utilize the transiently chaotic dynamics mechanism in optimizat
ion problem efficiently, we have analyzed the dynamical procedure of the tr
ansiently chaotic neural network model and studied the function of the cruc
ial bifurcation parameter which governs the chaotic behavior of the system.
Based or! the dynamical analysis of the transiently chaotic neural network
model, chaotic annealing algorithm is also examined and improved. As an ex
ample, we applied chaotic annealing method to the traveling salesman proble
m and obtained good results.