Kollektivnye svoǐstva sistemy vzaimoobuchaiushchikhsia neǐronnykh seteǐ v informatsionnom pole.

Translated title of the contribution: Collective properties of the mutual-learned neuronal net systems in the information field

A. I. Grosberg, N. V. Khrustova

    Research output: Contribution to journalArticle

    Abstract

    Model of neural networks system, in which networks interact by transmission and associative recognition of signals, is studied by computer simulation and qualitative approach. System behavior depends on the value of learning parameter epsilon, which determines the weight of writing in memory of each network every transmissible signal. Two different regimes are found: regime of auto-governed behavior, which depends only on initial networks characteristics, and regime of collective recognition of initial signal in form of a certain stable signals cycle. Analogy of this model and Aigen's hypercycle, the problem of creation of some new information in this model are discussed, too.

    Original languageUndefined
    Pages (from-to)726-735
    Number of pages10
    JournalBiofizika
    Volume38
    Issue number4
    StatePublished - Jul 1993

    Fingerprint

    Information Systems
    Neural Networks (Computer)
    Computer Simulation
    Learning
    Weights and Measures
    Recognition (Psychology)

    ASJC Scopus subject areas

    • Biophysics

    Cite this

    Kollektivnye svoǐstva sistemy vzaimoobuchaiushchikhsia neǐronnykh seteǐ v informatsionnom pole. / Grosberg, A. I.; Khrustova, N. V.

    In: Biofizika, Vol. 38, No. 4, 07.1993, p. 726-735.

    Research output: Contribution to journalArticle

    Grosberg, A. I. ; Khrustova, N. V. / Kollektivnye svoǐstva sistemy vzaimoobuchaiushchikhsia neǐronnykh seteǐ v informatsionnom pole. In: Biofizika. 1993 ; Vol. 38, No. 4. pp. 726-735.
    @article{2aa9bfb884334e7da13bf4b99702fada,
    title = "Kollektivnye svoǐstva sistemy vzaimoobuchaiushchikhsia neǐronnykh seteǐ v informatsionnom pole.",
    abstract = "Model of neural networks system, in which networks interact by transmission and associative recognition of signals, is studied by computer simulation and qualitative approach. System behavior depends on the value of learning parameter epsilon, which determines the weight of writing in memory of each network every transmissible signal. Two different regimes are found: regime of auto-governed behavior, which depends only on initial networks characteristics, and regime of collective recognition of initial signal in form of a certain stable signals cycle. Analogy of this model and Aigen's hypercycle, the problem of creation of some new information in this model are discussed, too.",
    author = "Grosberg, {A. I.} and Khrustova, {N. V.}",
    year = "1993",
    month = "7",
    language = "Undefined",
    volume = "38",
    pages = "726--735",
    journal = "Biofizika",
    issn = "0006-3029",
    publisher = "Izdatel'stvo Nauka",
    number = "4",

    }

    TY - JOUR

    T1 - Kollektivnye svoǐstva sistemy vzaimoobuchaiushchikhsia neǐronnykh seteǐ v informatsionnom pole.

    AU - Grosberg, A. I.

    AU - Khrustova, N. V.

    PY - 1993/7

    Y1 - 1993/7

    N2 - Model of neural networks system, in which networks interact by transmission and associative recognition of signals, is studied by computer simulation and qualitative approach. System behavior depends on the value of learning parameter epsilon, which determines the weight of writing in memory of each network every transmissible signal. Two different regimes are found: regime of auto-governed behavior, which depends only on initial networks characteristics, and regime of collective recognition of initial signal in form of a certain stable signals cycle. Analogy of this model and Aigen's hypercycle, the problem of creation of some new information in this model are discussed, too.

    AB - Model of neural networks system, in which networks interact by transmission and associative recognition of signals, is studied by computer simulation and qualitative approach. System behavior depends on the value of learning parameter epsilon, which determines the weight of writing in memory of each network every transmissible signal. Two different regimes are found: regime of auto-governed behavior, which depends only on initial networks characteristics, and regime of collective recognition of initial signal in form of a certain stable signals cycle. Analogy of this model and Aigen's hypercycle, the problem of creation of some new information in this model are discussed, too.

    UR - http://www.scopus.com/inward/record.url?scp=0027630498&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0027630498&partnerID=8YFLogxK

    M3 - Article

    VL - 38

    SP - 726

    EP - 735

    JO - Biofizika

    JF - Biofizika

    SN - 0006-3029

    IS - 4

    ER -