CaltechAUTHORS
  A Caltech Library Service

Capacity of Two-Layer Networks with Binary Weights

Ji, Chuanyi and Psaltis, Demetri (1993) Capacity of Two-Layer Networks with Binary Weights. In: Proceedings. IEEE International Symposium on Information Theory. IEEE , Piscataway, NJ, p. 434. ISBN 0-7803-0878-6. https://resolver.caltech.edu/CaltechAUTHORS:20170525-173839521

[img] PDF - Published Version
See Usage Policy.

115Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20170525-173839521

Abstract

The capacity C_b of two later (N - 2L - 1) feed-forward neural networks is shown to satisfy the relation O(W/(lnW)) ≤ C ≤ O(W). Here N - 2L - 1 stands for the networks with N input units, 2L hidden units and one output unit. W is the total number of weights of the networks. The weights take only binary values and the hidden units have integer thresholds.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/ISIT.1993.748750DOIArticle
http://ieeexplore.ieee.org/document/748750/PublisherArticle
Additional Information:© 1993 IEEE.
Record Number:CaltechAUTHORS:20170525-173839521
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20170525-173839521
Official Citation:Chuanyi Ji and D. Psaltis, "Capacity of Two-Layer Networks with Binary Weights," Proceedings. IEEE International Symposium on Information Theory, 1993, pp. 434-434. doi: 10.1109/ISIT.1993.748750
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:77787
Collection:CaltechAUTHORS
Deposited By: Kristin Buxton
Deposited On:26 May 2017 17:18
Last Modified:03 Oct 2019 18:01

Repository Staff Only: item control page