Erlanson, Ruth and Abu-Mostafa, Yaser (1991) Analog Neural Networks as Decoders. In: Advances in Neural Information Processing Systems 3. Morgan Kaufmann , San Mateo, CA, pp. 585-588. ISBN 1-55860-184-8. https://resolver.caltech.edu/CaltechAUTHORS:20160119-162724779
![[img]](https://authors.library.caltech.edu/style/images/fileicons/application_pdf.png) |
PDF
- Published Version
See Usage Policy. 861kB |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20160119-162724779
Abstract
Analog neural networks with feedback can be used to implement l(Winner-Take-All (KWTA) networks. In turn, KWTA networks can be used as decoders of a class of nonlinear error-correcting codes. By interconnecting such KWTA networks, we can construct decoders capable of decoding more powerful codes. We consider several families of interconnected KWTA networks, analyze their performance in terms of coding theory metrics, and consider the feasibility of embedding such networks in VLSI technologies.
| Item Type: | Book Section | ||||||
|---|---|---|---|---|---|---|---|
| Related URLs: |
| ||||||
| Additional Information: | © 1991 Morgan Kaufmann. | ||||||
| Record Number: | CaltechAUTHORS:20160119-162724779 | ||||||
| Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20160119-162724779 | ||||||
| Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||
| ID Code: | 63783 | ||||||
| Collection: | CaltechAUTHORS | ||||||
| Deposited By: | INVALID USER | ||||||
| Deposited On: | 20 Jan 2016 00:39 | ||||||
| Last Modified: | 03 Oct 2019 09:31 |
Repository Staff Only: item control page
