Pattern recognition using a hybrid computer

C.A.P.G. van der Mast

Mathematics and Computers in Simulation (MATCOM), 1972, vol. 14, issue 2, 63-64

Abstract: A method is developed for hybrid simulation of a linear sequential learning algorithm. Up to 60 weights can be corrected very fast simultaneously. Computing times are mainly dependent on speed of presentation of the patterns to the analogue computer. One type of analogue circuit seemed most suitable for implementation in special purpose hard-ware. The method is convenient for interaction with the user.

Date: 1972
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378475472800338
Full text for ScienceDirect subscribers only

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:eee:matcom:v:14:y:1972:i:2:p:63-64

DOI: 10.1016/S0378-4754(72)80033-8

Access Statistics for this article

Mathematics and Computers in Simulation (MATCOM) is currently edited by Robert Beauwens

More articles in Mathematics and Computers in Simulation (MATCOM) from Elsevier
Bibliographic data for series maintained by Catherine Liu ().