Abstract
One technique that uses Wang’s Recurrent Neural Networks with the “Winner Takes All” principle is presented to solve the Assignment problem. With proper choices for the parameters of the Recurrent Neural Network, this technique reveals to be efficient solving the Assignment problem in real time. In cases of multiple optimal solutions or very closer optimal solutions, the Wang’s Neural Network does not converge. The proposed technique solves these types of problem. Comparisons between some traditional ways to adjust the RNN’s parameters are made, and some proposals concerning to parameters with dispersion measures of the problem’s cost matrix’ coefficients are show.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ahuja, R.K., Mangnanti, T.L., Orlin, J.B.: Network Flows. Theory, Algorithms and Applications. Prentice Hall, New Jersey (1993)
Bazaraa, M.S., Jarvis, J.J., Sherali, H.D.: Linear Programming and Network Flows, 2nd edn. Wiley, New York (1990)
Siqueira, P.H., Carnieri, C., Steiner, M.T.A., Barboza, A.O.: Uma proposta de solução para o problema da construção de escalas de motoristas e cobradores de ônibus por meio do algoritmo do matching de peso máximo. Gestão & Produção 11, 187–196 (2004)
Hopfield, J.J., Tank, D.W.: Neural Computation of decisions in optimization problems. Biological Cybernetics 52, 141–152 (1985)
Matsuda, S.: Optimal. Hopfield network for combinatorial optimization with linear cost function. IEEE Transactions on Neural Networks 9, 1319–1330 (1998)
Wang, J.: Analog Neural Network for Solving the Assignment Problem. Electronic Letters 28, 1047–1050 (1992)
Wang, J.: Primal and Dual Assignment Networks. IEEE Transactions on Neural Networks 8, 784–790 (1997)
Wang, J.: Analysis and Design of a Recurrent Neural Network for Linear Programming. IEEE Transactions on Circuits and Systems 40, 613–618 (1993)
Hung, D.L., Wang, J.: Digital Hardware Realization of a Recurrent Neural Network for Solving the Assignment Problem. Neurocomputing 51, 447–461 (2003)
Wang, J.: A Deterministic Annealing Neural Network for Convex Programming. Neural Networks 7, 629–641 (1994)
Wang, J.: Analysis and Design of a analog Sorting Network. IEEE Transactions on Neural Networks 6, 962–971 (1995)
Liu, D., Hu, S., Wang, J.: Global Output Convergence of a Class of Continuous-Time Recurrent Neural Networks with Time-Varying Thresholds. IEEE Transactions on Circuits and Systems 51, 161–167 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Siqueira, P.H., Scheer, S., Steiner, M.T.A. (2005). Application of the “Winner Takes All” Principle in Wang’s Recurrent Neural Network for the Assignment Problem. In: Wang, J., Liao, X., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427391_117
Download citation
DOI: https://doi.org/10.1007/11427391_117
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25912-1
Online ISBN: 978-3-540-32065-4
eBook Packages: Computer ScienceComputer Science (R0)