Counterpropagation networks

Clicks: 267
ID: 113880
1987
Free PDF
Article Quality & Performance Metrics
Overall Quality Improving Quality
0.0 /100
Combines engagement data with AI-assessed academic quality
AI Quality Assessment
Not analyzed
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 closed-form 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.
Reference Key
hecht-nielsen1987appliedcounterpropagation Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Robert Hecht-Nielsen;Robert Hecht-Nielsen;
Journal Applied optics
Year 1987
DOI
doi:10.1364/AO.26.004979
URL
https://dx.doi.org/10.1364/AO.26.004979
Keywords
statistics pattern recognition neural networks interpolation systems design National Center for Biotechnology Information NCBI NLM MEDLINE pubmed abstract nih national institutes of health national library of medicine pmid:20523476 doi:10.1364/ao.26.004979 r hecht-nielsen

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.