A chaotic annealing neural network and its application to direction estimation of spatial signal sources

A chaotic annealing neural network model based on transient chaos and dynamic gain is proposed for solving optimization problems with continuous-variables, such as the maximal likelihood estimation of spatial signal sources considered in this article. Compared to conventional neural networks only with point attractors, the proposed neural network has richer and more flexible dynamics, which are expected to have higher ability of searching for globally optimal or near-optimal solutions. After going through an inverse-bifurcation process, the neural network gradually approaches to a conventional Hopfield neural network, starting from a good initial state. Numerical simulations show both the effectiveness on escaping from local minima and the ability for solving nonlinear maximal likelihood estimation of spatial sources of the proposed network