Matematicheskoe modelirovanie
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive
Impact factor

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Matem. Mod.:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Matematicheskoe modelirovanie, 1992, Volume 4, Number 10, Pages 101–110 (Mi mm2124)  

Computational methods and algorithms

Neural nets for correlated and non-binary patterns: feedback from current pattern to neuron response and threshold

B. M. Balter, I. V. Popova

Space Research Institute
Abstract: We analyse the mechanism by which Hopfield algorithm suppresses all patterns but one. We modify it by adapting the neuron response function and the threshold in each node to the global current pattern and to overall correlation among memory patterns. Such feedback lets the method recognize strongly correlated memories and operate on non-binary neurons (that is, those with more states than just 0,1).
Received: 25.09.1992
Bibliographic databases:
Language: Russian
Citation: B. M. Balter, I. V. Popova, “Neural nets for correlated and non-binary patterns: feedback from current pattern to neuron response and threshold”, Matem. Mod., 4:10 (1992), 101–110
Citation in format AMSBIB
\Bibitem{BalPop92}
\by B.~M.~Balter, I.~V.~Popova
\paper Neural nets for correlated and non-binary patterns: feedback from current pattern to neuron response and threshold
\jour Matem. Mod.
\yr 1992
\vol 4
\issue 10
\pages 101--110
\mathnet{http://mi.mathnet.ru/mm2124}
\mathscinet{http://mathscinet.ams.org/mathscinet-getitem?mr=1219034}
\zmath{https://zbmath.org/?q=an:1189.68092}
Linking options:
  • https://www.mathnet.ru/eng/mm2124
  • https://www.mathnet.ru/eng/mm/v4/i10/p101
  • Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Математическое моделирование
    Statistics & downloads:
    Abstract page:558
    Full-text PDF :270
    First page:1
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024