DocumentCode :
395504
Title :
Characteristic updating-normalisation dynamics of a self-organising neural network for enhanced combinatorial optimisation
Author :
Kwok, Terence ; Smith, Kate A.
Author_Institution :
Sch. of Bus. Syst., Monash Univ., Clayton, Vic., Australia
Volume :
3
fYear :
2002
fDate :
18-22 Nov. 2002
Firstpage :
1146
Abstract :
The optimisation performance of a self-organising neural network with weight normalisation (SONN-WN) is computationally studied in this paper. The SONN-WN is applied to solve the constraint satisfaction problem (CSP) of N-queen, and performance indicators such as feasibility and efficiency are measured in the key parameter space of the Kohonen learning rate β and normalisation temperature T. The measurements reveal regions of high optimisation ability associated with certain β and T combinations, indicating the close coupling of the Kohonen learning and normalisation mechanisms towards effective optimisation. The complex interaction of the two mechanisms is studied by numerically investigating the nonlinear dynamics of a simplified model of the updating-normalisation process. By combining the performance measurements of the SONN-WN with the dynamical study of the simplified model, a range of characteristic convergence dynamics have been identified with the SONN-WN for enhanced optimisation performance.
Keywords :
combinatorial mathematics; convergence of numerical methods; optimisation; self-organising feature maps; Kohonen learning rate; combinatorial optimisation; constraint satisfaction problem; convergence; n-queen problem; nonlinear dynamics; self-organising neural network; weight normalisation; Annealing; Australia; Computer networks; Constraint optimization; Convergence; Neural networks; Temperature control; Temperature measurement; Temperature sensors; Traveling salesman problems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
Type :
conf
DOI :
10.1109/ICONIP.2002.1202801
Filename :
1202801
Link To Document :
بازگشت