Abstract
The behavior of a Boltzmann Machine (BM) according to changes in the parameters that determine its convergence is experimentally analyzed to find a way to accelerate the convergence towards a solution for the given optimization problem. The graph colouring problem has been chosen as a benchmark for which convergence with quadratic time complexity has been obtained.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Aarts, E.H.L., Korst, J.H.M.: Simulated Annealing and Boltzmann Machines. Wiley, New York (1989)
Chow, F., Hennessy, J.: Register Allocation by Priority-Based Colouring. Proceedings of the ACM SIGPLAN’ 84. Symposium on Compiler Construction SIGPLAN Notices, vol. 19,num.6, (June 1984)
Ortega, J., and others: Parallel Coarse Grain Computing of Boltzmann Machines. Neural Processing Letters 7: 169–184, (1998)
Kappen, H.J., RodrÃguez, F.B.: Efficient Learning in Boltzmann Machines Using Linear Response Theory. Neural Computation 10(5): 1137–1156, (1998)
Garey, M.R., Johnson, D.S.: Computers and Intractability: A Guide to the Theory of NPCompleteness. Freeman (1979)
Zissimopoulos, V., Paschos, V.Th., Pekergin, F.:On the Approximation of NP-Complete Problems by Using the Bolzmann Machine Method: The Cases of Some Covering and Packing Problems. IEEE Transactions on Computers, vol. 40,num. 12, (December 1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Javier Salcedo, F., Ortega, J., Prieto, A. (2001). Analyzing Boltzmann Machine Parameters for Fast Convergence. In: Mira, J., Prieto, A. (eds) Bio-Inspired Applications of Connectionism. IWANN 2001. Lecture Notes in Computer Science, vol 2085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45723-2_17
Download citation
DOI: https://doi.org/10.1007/3-540-45723-2_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42237-2
Online ISBN: 978-3-540-45723-7
eBook Packages: Springer Book Archive