Competition based neural networks for assignment problems
Competition based neural networks have been used to solve the generalized assignment problem and the quadratic assignment problem. Both problems are very difficult and are ε approximation complete. The neural network approach has yielded highly competitive performance and good performance for the quadratic assignment problem. These neural networks are guaranteed to produce feasible solutions.
KeywordsNeural Network Feasible Solution Energy Function Assignment Problem Combinatorial Optimization Problem
Unable to display preview. Download preview PDF.
- L-Y. Fang, Design of Computational Neural Networks. Ph. D. thesis submitted to the Flinders University of South Australia, March 1990.Google Scholar
- Y. Peng and J. Reggia, A connectionist model for diagnostic problem solving.IEEE Trans. Syst. Man and Cybernetics, SMC-19 (1989).Google Scholar
- J. Reggia, Methods for deriving competitive activation mechanisms. Int Joint Conf. Neural Networks, (June 1989) Washington D. C., 357–363.Google Scholar
- T. Li and L-Y Fang, Parallel approximate solution of 0/1 knapsack optimization on competitive neural network. to appear inAdvances in Parallel Computing, Vol. 3, 1990, North-Holland.Google Scholar