Part of the Lecture Notes in Control and Information Sciences book series (LNCIS, volume 130)
Non-binary neural networks
On capacity considerations it is clear that it is advantageous to use non-binary neural networks.
Unable to display preview. Download preview PDF.
- 1.Lance M. Optican and Barry J. Richmond, “Temporal Encoding of Two-Dimensional Patterns by Single Units in Primate Inferior Temporal Cortex. III. Information Theoretic Analysis,” Journal of Neurophysiology, vol. 57, no. 1, pp. 163–178, January 1987.Google Scholar
- 2.Subhash C. Kak, “CHAOTIC STATES OF MIND—Neural Networks with Nonclassical Synaptic Function,” Louisiana State University, Technical Report #50-88, Baton Rouge, LA, April 29, 1988.Google Scholar
- 3.Donald L. Prados, “The Capacity of a Neural Network,” Electronics Letters, vol. 24, pp. 454–455, 1988.Google Scholar
- 4.T. W. Potter, “Storing and Retrieving Data in a Parallel Distributed Memory System,” SUNY at Binghamton, Ph.D. Dissertation, 1987.Google Scholar
- 5.R. J. McEliece, E. C. Posner, E. R. Rodemich, and S. S. Venkatesh, “The Capacity of the Hopfield Associative Memory,” IEEE Transactions on Information Theory, vol. IT-33, pp. 461–482, 1987.Google Scholar
© Springer-Verlag 1989