C.-K. Pham and W. Noguchi (Japan)
N-Queen problem, Hopfield neural network, hardware accelerator.
A hardware accelerator for solving the N-Queen problem is presented. It has been designed to perform an effective solving method with a modified hill-climbing term which is applied to a maximum neuron model for solving the N Queen problems. In the solving method, a first model using a gradient ascent learning for determining A and B coeffi cients, a second model using fixed A and B coefficients which are determined by an upper bound of an input value to a neuron, and a third model using modified initial val ues which applied to the second model, have been adopted. As a result, calculation times are reduced up to 40% when compared with the previous methods. And, the hardware accelerator gives up to 25 times of higher speed when com pared with software running by the PC.
Important Links:
Go Back
