Abstract
The potential of neural networks to find global optimum should be further explored. Their ability to do so using only local “gradient” information is surprising and can lead to very useful applications. Implementing an optimum receiver-decoder is a particularly interesting example.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
J. J. Hopfield, “Neural networks and physical systems with emerging collective computational abilities,” Proc. National Academy of Sciences 79 (1982) 2554–2558.
S. Kirkpatrick, C. D. Gelatt, Jr. and M. P. Vecchi, “Optimization by simulated annealing,” Science 220 (1983) 671–680.
E. Wong, “Stochastic neural networks,” Algorithmica 6 (1991) 466–478.
E. Wong, “Implementing Boltzmann machines,” in Stochastic Analysis, E. Mayer-Wolf, E. Merzbach and A. Schwartz, eds., Academic Press, San Diego, 1991.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wong, E. (1992). Neural computing and stochastic optimization. In: Bensoussan, A., Verjus, J.P. (eds) Future Tendencies in Computer Science, Control and Applied Mathematics. INRIA 1992. Lecture Notes in Computer Science, vol 653. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56320-2_70
Download citation
DOI: https://doi.org/10.1007/3-540-56320-2_70
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56320-4
Online ISBN: 978-3-540-47520-0
eBook Packages: Springer Book Archive