Think positive to find parts

Bartlett W. Mel ()
Additional contact information
Bartlett W. Mel: University of Southern California

Nature, 1999, vol. 401, issue 6755, 759-760

Abstract: What are the 'features' or 'parts' that our brains use to tell one thing from another? Several algorithms exist for learning object parts, and the development of the latest -- known as non-negative matrix factorization -- is now reported. This algorithm seems to decompose sets of faces into 'basis functions' that are different, and more part-like, than those found by conventional algorithms.

Date: 1999
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/44507 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:401:y:1999:i:6755:d:10.1038_44507

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/44507

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().