A neural network for shortest path computation

  title={A neural network for shortest path computation},
  author={Filipe Ara{\'u}jo and Bernardete Ribeiro and Lu{\'i}s E. T. Rodrigues},
  journal={IEEE transactions on neural networks},
  volume={12 5},
This paper presents a new neural network to solve the shortest path problem for inter-network routing. [...] Key Method This new method addresses some of the limitations of previous solutions, in particular the lack of reliability in what concerns successful and valid convergence. Experimental results show that an improvement in successful convergence can be achieved in certain classes of graphs. Additionally, computation performance is also improved at the expense of slightly worse results.Expand
Solving the Shortest Path Routing Problem Using Noisy Hopfield Neural Networks
  • Wen Liu, Lipo Wang
  • Computer Science
  • 2009 WRI International Conference on Communications and Mobile Computing
  • 2009
To improve neural network algorithms for the shortest path routing problem (SPRP), we propose a solution using a noisy Hopfield neural network (NHNN), i.e., by adding decaying stochastic noise to theExpand
A Neural-network Algorithm for All k Shortest Paths Problem
The progress of extending a neural network algorithm to solve the KSP problem is reported and how to apply the new KSP algorithm to a whole-genome sequencing problem is discussed. Expand
Accumulative competition neural network for shortest path tree computation
Shortest path tree (SPT) computation is an important combinatorial optimization problem with numerous applications. A novel neural network model called accumulative competition neural network (ACNN)Expand
A Minimum Resource Neural Network Framework for Solving Multiconstraint Shortest Path Problems
The framework guarantees globally optimal solutions of a series of problems during the iteration process of the network, which provides insight into why even the SP is still too long to be satisfied. Expand
Biased Consensus Based Distributed Neural Network
This chapter discusses a neural network method for handling the shortest path problem with one or multiple alternative destinations and analyzes the effectiveness of the presented neural networks in theory and also gives computer simulations to demonstrate the performance of the neural networks. Expand
A two-layer recurrent Neural Network based approach for overlay multicast
A neural network for overlay multicast tree computation is presented to reliably implement routing algorithm in real time, characterized as shorter computational time, fewer neurons, and better precision compared with the heuristic routing algorithms. Expand
Implementations of Hopfield neural network in communication networks
  • N. Kojić
  • Computer Science
  • 2013 21st Telecommunications Forum Telfor (TELFOR)
  • 2013
The possibility of intelligent decision making of Hopfield neural network, through the three independent implementations, will be presented and one possible solution for multicast routing in telecommunication networks as well as routing in all optical networks is presented. Expand
Neural Network based Dynamic Multicast Routing
The Hopfield neural network is suggested for dynamic multicast routing in communication network of arbitrary topology and under variable traffic conditions and a new algorithm takes into account not only the actual network state, but also the history of link/router occupancy. Expand
Hopfield-genetic approach for solving the routing problem in computer networks
  • M. Hamdan, M. El-Hawary
  • Computer Science
  • IEEE CCECE2002. Canadian Conference on Electrical and Computer Engineering. Conference Proceedings (Cat. No.02CH37373)
  • 2002
A method that combines Hopfield networks (HN) and a genetic algorithm (GA) to solve the problem of optimal routing in computer networks and shows an improvement in the quality of the solution and reduces the computation time. Expand
A type of biased consensus-based distributed neural network for path planning
In this paper, a unified scheme is proposed for solving the classical shortest path problem and the generalized shortest path problem, which are highly nonlinear. Particularly, the generalizedExpand


Neural networks for shortest path computation and routing in computer networks
An efficient neural network shortest path algorithm that is an improved version of previously suggested Hopfield models is proposed that will enable the routing algorithm to be implemented in real time and also to be adaptive to changes in link costs and network topology. Expand
Neural network implementation of the shortest path algorithm for traffic routing in communication networks
A neural network computation algorithm is introduced to solve the optimal traffic routing in a general N-node communication network and the knowledge about the number of links between each origin-destination pair is not required by the algorithm, therefore it can be applied to a more general network. Expand
A neural network based multi-destination routing algorithm for communication network
  • Dong-Chul Park, Seungwon Choi
  • Computer Science
  • 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227)
  • 1998
The results show improvements in both computational performance and solution optimality by the proposed approach over conventional approaches. Expand
Neural networks for routing communication traffic
The use of neural network computational algorithms to determine optimal traffic routing for communication networks is introduced and results show reasonable convergence in 250 iterations for a 16-node network with up to four links from origin to destination. Expand
“Neural” computation of decisions in optimization problems
Results of computer simulations of a network designed to solve a difficult but well-defined optimization problem-the Traveling-Salesman Problem-are presented and used to illustrate the computational power of the networks. Expand
Flows in Networks.
In this classic book, first published in 1962, L. R. Ford, Jr., and D. R. Fulkerson set the foundation for the study of network flow problems. The models and algorithms introduced in Flows inExpand
Network optimization : continuous and discrete models
Telecommunication networks