Dual-mode dynamics neural network for non-attacking N-Queen problem

A new approach for solving combinatorial optimization problems is presented, based on a novel dynamic neural network featuring a dual-mode of network dynamics, the state dynamics and the weight dynamics. The major difficulties in the neural network approaches for optimization problems are: (1) the objective function for a given problem should have a form that can be mapped onto the network; and (2) due to the local minima problem, the quality of the solution is quite sensitive to various factors, such as the initial state, the parameters in the objective function, etc. The proposed scheme solves these problems: (1) by maintaining the objective function separately from the network energy function, rather than mapping it onto the network, and (2) by introducing the weight dynamics utilizing the objective function to overcome the local minima problem