The minimum cost path finding algorithm using a Hopfield type neural network
Sun-Gi Hong, Sung-Woo Kim, Ju-Jang Lee · 2002
Neural networks have been proposed as new computational tools for solving constrained optimization problems. In this paper the minimum cost path finding algorithm is proposed by using a Hopfield type neural network. In order to design a Hopfield type neural network, an energy function must be defined at first. To achieve this, the concept of a vector-represented network is used to describe the connected path. Through simulations, it will be shown that the proposed algorithm works very well in many cases. The local minima problem of a Hopfield type neural network is discussed.>