Title :
An asynchronous neural network model for shortest path problem
Author :
Zhao, Songhe ; Dillon, T.S.
Author_Institution :
Expert intelligen Syst. Lab., La Trobe Univ., Bundoora, Vic., Australia
Abstract :
Most neural network models are energy based models and there is no guarantee that the network converges to a global optimal solution. A new neural shortest path network model is proposed in which no special convergence procedure needs to be performed. The network can work in a purely asynchronous mode, and is guaranteed to reach the global optimal solution
Keywords :
neural nets; optimisation; asynchronous neural network model; global optimal solution; purely asynchronous mode; shortest path problem; Algorithm design and analysis; Computer networks; Computer science; Intelligent networks; Intelligent systems; Laboratories; Neural networks; Neurons; Power engineering and energy; Shortest path problem;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298689
