Summary
To increase the computing speed of neural networks by means of parallel performance, a new mode of neural network, named Tri-state Cascading Pulse Coupled Neural Network (TCPCNN), is presented in this paper, which takes the ideas of three-state and pipelining used in circuit designing into neural network, and creates new neuron with three states: sub-firing, firing and inhibition. The proposed model can transmit signals in parallel way, as it is inspired not only in the direction of auto-wave propagation but also in its transverse direction in neural network. In this paper, TCPCNN is applied to find the shortest path, and the experimental results indicate that the algorithm has lower computational complexity, higher accuracy, and secured full-scale searching. Furthermore, it has little dependence on initial conditions and parameters. The algorithm is tested by some experiments, and its results are compared with some other classical algorithms - Dijkstra algorithm, Bellman-Ford algorithm and a new algorithm using pulse coupled neural networks.
See the full content of this document
Extract
Tri-State Cascading Pulse Coupled Neural Network and Its Application in Finding Shortest Path
(ProQuest: ... denotes formulae omitted.)
1. IntroductionPulse Coupled Neural Network [1, 2] (PCNN), different from the conventional artificial neural networks, was formed and developed in the 1990s by Eckhron et al. It is based on Eckhorn's neuron model, and derives from the phenomena of synchronous pulse bursts in mammals (cats, monkeys, etc.) visual cortex. The auto-wave [3] nature of PCNN, defined as normal propagating waves that do not reflect or refract, makes it useful.Shortest Path (SP) problem is to find the shortest path between a given source and a destination in a network. Here, the "shortest" means that the total cost corresponding with a path is least or the length of a path from source to destination is minimal. Same as the well-known Traveling Salesman Problem (TSP) and Maze Problem, the SP is an optimization problem with diverse applications, such as vehicle routing in transportation, path layout in robot system, website page searching in internet, data compressing, traffic routing in communication networks and so on.There are many methods to solve the SP problem, fo...See the full content of this document
Sponsored links
