A Model of Chaotic Neural Network With Applications in Optimization
Qiang Zhang · Systems engineering and electronics · 2002
A neural network model with transient chaotic dynamic behaviors is proposed by introducing a nonlinear self-feedback into canonical Hopfield neural networks(HNN). The model gradually approaches,through reversed period-doubling bifurcations, to a dynamical structure similar to the Hopfield neural network which converges to a stable equilibrium point. As the model has rich dynamics, it can be expected to have robust searching ability for globally optimal solutions. Finally, two examples of function optimization are given to show the validity of this model.