Published February 1, 1985
| public
Journal Article
Open
Optical information processing based on an associative-memory model of neural nets with thresholding and feedback
- Creators
- Psaltis, Demetri
- Farhat, Nabil
Abstract
The remarkable collective computational properties of the Hopfield model for neural networks [Proc. Nat. Acad. Sci. USA 79, 2554 (1982)] are reviewed. These include recognition from partial input, robustness, and error-correction capability. Features of the model that make its optical implementation attractive are discussed, and specific optical implementation schemes are given.
Additional Information
© Copyright 1985 Optical Society of America Received July 9, 1984; accepted November 15, 1984 The authors thank John Hong and Yaser Abu-Mostafa for many helpful discussions on this subject.Files
PSAol85.pdf
Files
(499.9 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:7bc022af2c809f37036d523d81f8eaf4
|
499.9 kB | Preview Download |
Additional details
- Eprint ID
- 3265
- Resolver ID
- CaltechAUTHORS:PSAol85
- Created
-
2006-05-25Created from EPrint's datestamp field
- Updated
-
2019-10-02Created from EPrint's last_modified field