The Minimum Cost Path Finding Algorithm Using a Hopfield Type Neural Network
نویسندگان
چکیده
Recently neural networks have been ploposed as new computational tools for solving constrained optimization problems. In this paper the minimum cost path fmding algorithm is proposed by using a Hopfield type neural network. In order to design a Hopfield type neural network, an energy function must be defmed at f i t . To achieve thii, 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.
منابع مشابه
Neural Networks and Optimization Problems A Case Study: The Minimum Cost Spare Allocation Problem
We are interested in finding near-optimal solutions to hard optimization problems using Hopfield-type neural networks. The methodology is based on a basic property of such networks, that of reducing their ‘energy’ during evolution, leading to a local or global minimum. The methodology is presented and several different network models usually employed as optimizers (Analog Hopfield net with Simu...
متن کاملNear-Optimal Solutions for the Minimum Cost Spare Allocation Problem using Hopfield-Type Neural Network Optimizers1
Four neural network models (analog Hopfield network with simulated annealing, Boltzmann machine, Cauchy machine and a hybrid scheme) are reviewed and subsequently employed as optimizers in order to solve the NP-HARD Minimum Cost Spare Allocation (MCSA) Problem (or equivalently Vertex Cover in bipartite graphs). The methodology is based on the energy reduction property of such networks and provi...
متن کاملNeural Network Modelling of Optimal Robot Movement Using Branch and Bound Tree
In this paper a discrete competitive neural network is introduced to calculate the optimal robot arm movements for processing a considered commitment of tasks, using the branch and bound methodology. A special method based on the branch and bound methodology, modified with a travelling path for adapting in the neural network, is introduced. The main neural network of the system consists of diff...
متن کاملOptimum Design of Liquified Natural Gas Bi-lobe Tanks using Finite Element, Genetic Algorithm and Neural Network
A comprehensive set of ten artificial neural networks is developed to suggest optimal dimensions of type ‘C’ Bi-lobe tanks used in the shipping of liquefied natural gas. Multi-objective optimization technique considering the maximum capacity and minimum cost of vessels are implemented for determining optimum vessel dimensions. Generated populations from a genet...
متن کاملEfficient and optimal binary Hopfield associative memory storage using minimum probability flow
We present an algorithm to store binary memories in a Hopfield neural network using minimum probability flow, a recent technique to fit parameters in energybased probabilistic models. In the case of memories without noise, our algorithm provably achieves optimal pattern storage (which we show is at least one pattern per neuron) and outperforms classical methods both in speed and memory recovery...
متن کامل