Solving the Shortest Path Routing Problem Using Noisy Hopfield Neural Networks

Author

Liu, Wen ; Wang, Lipo

Author_Institution

Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore

Volume

fYear

2009

fDate

6-8 Jan. 2009

Firstpage

299

Lastpage

302

Abstract

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 the continuous Hopfield neural network (HNN). We also modify the energy function for the SPRP. Simulation results show that our approach achieves better route optimality compared to other algorithms that employ the HNN.

Keywords

Hopfield neural nets; graph theory; stochastic processes; telecommunication network routing; continuous Hopfield neural network; decaying stochastic noise; energy function; noisy Hopfield neural network; route optimality; shortest path routing problem; Communication networks; Costs; Hopfield neural networks; Mobile communication; Network topology; Neural networks; Neurons; Recurrent neural networks; Routing; Very large scale integration; Hopfield Neural Networks; Noisy; Routing; Shortest Path;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Mobile Computing, 2009. CMC '09. WRI International Conference on

Conference_Location

Yunnan

Print_ISBN

978-0-7695-3501-2

Type

conf

DOI

10.1109/CMC.2009.366

Filename

4797136

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2937143