Cortese, John A. and Goodman, Rodney M. (1994) A statistical analysis of neural computation. In: Proceedings of 1994 IEEE International Symposium on Information Theory. IEEE , Piscataway, NJ, p. 215. ISBN 0780320158. https://resolver.caltech.edu/CaltechAUTHORS:20190315-142359458
![]() |
PDF
- Published Version
See Usage Policy. 73Kb |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190315-142359458
Abstract
This paper presents an architecture and learning algorithm for a feedforward neural network implementing a two pattern (image) classifier. By considering the input pixels to be random variables, a statistical binary hypothesis (likelihood ratio) test is implemented. A linear threshold separates p[X|H_0] and p[X|H_1], minimizing a risk function. In this manner, a single neuron is considered as a BSC with the pdf error tails probability ε. A Single layer of neurons is viewed as a parallel bank of independent BSC’s, which is equivalent to a single effective BSC representing that layer’s hypothesis testing performance. A multiple layer network is viewed as a cascade of BSC channels, and which again collapses into a single effective BSC.
Item Type: | Book Section | ||||||
---|---|---|---|---|---|---|---|
Related URLs: |
| ||||||
Additional Information: | © 1994 IEEE. | ||||||
Record Number: | CaltechAUTHORS:20190315-142359458 | ||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20190315-142359458 | ||||||
Official Citation: | J. A. Cortese and R. M. Goodman, "A statistical analysis of neural computation," Proceedings of 1994 IEEE International Symposium on Information Theory, Trondheim, Norway, 1994, pp. 215-. doi: 10.1109/ISIT.1994.394753 | ||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||
ID Code: | 93886 | ||||||
Collection: | CaltechAUTHORS | ||||||
Deposited By: | George Porter | ||||||
Deposited On: | 15 Mar 2019 22:16 | ||||||
Last Modified: | 03 Oct 2019 20:58 |
Repository Staff Only: item control page