Published August 21, 1989
| Published
Journal Article
Open
Mapping correlated Gaussian patterns in a perceptron
- Creators
- Fontanari, J. F.
- Meir, R.
Chicago
Abstract
The authors study the performance of a single-layer perceptron in realising a binary mapping of Gaussian input patterns. By introducing non-trivial correlations among the patterns, they generate a family of mappings including easier ones where similar inputs are mapped into the same output, and more difficult ones where similar inputs are mapped into different classes. The difficulty of the problem is gauged by the storage capacity of the network, which is higher for the easier problems.
Additional Information
Copyright © Institute of Physics and IOP Publishing Limited 1989. Received 10 May 1989, in final form 19 June 1989. Print publication: Issue 16 (21 August 1989). We thank the referee for pointing out a flaw in the original version of the manuscript. The research at Caltech was supported by contract N00014-87-K-0377 from the Office of Naval Research. JFF is partly supported by a CNPq (Brazil) fellowship and RM is supported by a Weizmann fellowship.Attached Files
Published - FONjpa89.pdf
Files
FONjpa89.pdf
Files
(298.2 kB)
Name | Size | Download all |
---|---|---|
md5:bd6257f2d3576d8fe2e7c1497672ff21
|
298.2 kB | Preview Download |
Additional details
- Eprint ID
- 12736
- Resolver ID
- CaltechAUTHORS:FONjpa89
- Office of Naval Research
- N00014-87-K-0377
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) (Brazil)
- Weizmann Institute
- Created
-
2008-12-22Created from EPrint's datestamp field
- Updated
-
2022-07-12Created from EPrint's last_modified field