Advances in Computer Science and Engineering
Volume 2, Issue 1, Pages 1 - 14
(March 2008)
|
|
AN IMPROVED DYNAMICS IN HOPFIELD NEURAL NETWORK FOR FINDING A NEAR-MAXIMUM INDEPENDENT SET OF A CIRCLE GRAPH
Rong-Long Wang (Japan), Shan-Shan Guo (Japan) and Kozo Okazaki (Japan)
|
Abstract:
In this paper, we present an improved dynamics in Hopfield neural network for finding a near-maximum independent set of a circle graph. The improved dynamics provides a mechanism for permitting temporary increases in the energy function in order to avoid local minima, by using a stabilization parameter to control the updating of neurons inputs. The method is tested through simulating some random graphs, with the simulation results showing that the solution found by the proposed method is superior to that of the best existing parallel algorithm. |
| Keywords and phrases: Hopfield neural network, local minimum, maximum independent
set, circle graph. |
| |
| Number of Downloads: 303 | Number of Views: 687 |
|
