Counterpropagation Networks

descriptionPublicationkeyboard_double_arrow_right Part of book or chapter of book , Article 01 Dec 1987 English Publisher:The MIT PressJournal:Applied Optics, volume 26, page 4,979 (issn: 0003-6935, eissn: 1539-4522,

Copyright policy )

Authors: R, Hecht-Nielsen;

doi: 10.7551/mitpress/5271.003.0010 , 10.1364/ao.26.004979

pmid: 20523476

Counterpropagation Networks

- Summary
- Metrics

Abstract

By combining Kohonen learning and Grossberg learning a new type of mapping neural network is obtained. This counterpropagation network (CPN) functions as a statistically optimal self-programming lookup table. The paper begins with some introductory comments, followed by the definition of the CPN. Then a closedform formula for the error of the network is developed. The paper concludes with a discussion of CPN variants and comments about CPN convergence and performance. References and a neurocomputing bibliography with a combined total of eighty entries are provided.

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	620
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Top 1%
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Top 0.01%
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Top 10%