Title :
An Improved Internal Dynamics in Binary Neural Network for Solving Optimization Problems
Author :
Wang, Rong Long ; Guo, Shan Shan ; Fukuta, Shinichi ; Zhang, Pei ; Okazak, Kozo
Author_Institution :
Fac. of Eng., Fukui Univ.
Abstract :
In this paper, an improved internal dynamics in binary neural network is proposed for efficiently solving combinatorial optimization problems. The improved internal dynamics provides a mechanism for increasing the exchange of information between neurons, by using a stabilization parameter to control the updating of neurons inputs. The performance was evaluated through simulating the N-queens problem. Simulation results showed that the proposed technique has improved the searching capability of the network and decreased computation time
Keywords :
combinatorial mathematics; neural nets; numerical stability; optimisation; binary neural network; combinatorial optimization problems; internal dynamics; stabilization parameter; Artificial neural networks; Computational modeling; Computer networks; Convergence; Heuristic algorithms; Information science; Intelligent networks; Neural networks; Neurons; Power engineering computing; Binary neural network; N-queens problem; combinatorial optimization problem; internal dynamics;
Conference_Titel :
Neural Networks and Brain, 2005. ICNN&B '05. International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9422-4
DOI :
10.1109/ICNNB.2005.1614884
