Bibliothek

feed icon rss

Ihre E-Mail wurde erfolgreich gesendet. Bitte prüfen Sie Ihren Maileingang.

Leider ist ein Fehler beim E-Mail-Versand aufgetreten. Bitte versuchen Sie es erneut.

Vorgang fortführen?

Exportieren
  • 1
    Digitale Medien
    Digitale Medien
    Springer
    Neural processing letters 12 (2000), S. 107-113 
    ISSN: 1573-773X
    Schlagwort(e): backpropagation ; regularization ; multilayer perceptron ; fault tolerance ; mean square sensitivity
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract When the learning algorithm is applied to a MLP structure, different solutions for the weight values can be obtained if the parameters of the applied rule or the initial conditions are changed. Those solutions can present similar performance with respect to learning, but they differ in other aspects, in particular, fault tolerance against weight perturbations. In this paper, a backpropagation algorithm that maximizes fault tolerance is proposed. The algorithm presented explicitly adds a new term to the backpropagation learning rule related to the mean square error degradation in the presence of weight deviations in order to minimize this degradation. The results obtained demonstrate the efficiency of the learning rule proposed here in comparison with other algorithm.
    Materialart: Digitale Medien
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 2
    Digitale Medien
    Digitale Medien
    Springer
    Analog integrated circuits and signal processing 13 (1997), S. 111-121 
    ISSN: 1573-1979
    Schlagwort(e): bio-inspired VLSI circuits ; spike processing neurons ; temporal interactions ; address-driven communication
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Elektrotechnik, Elektronik, Nachrichtentechnik
    Notizen: Abstract The paper presents a VLSI approach to approximate thereal-time dynamics of a neuron model inspired from the classicalmodel of Hodgkin and Huxley, in which analog inputs and outputsare represented by short spikes. Both the transient and the steady-statebehaviours of these circuits depend only on process-independentlocal ratios, thus enabling single or multiple-chip VLSI implementationsof very large analog neural networks in which parallelism, asynchronyand temporal interactions are kept as important neural processingfeatures. Measurements on an integrated CMOS prototype confirmexperimentally the expected electrical and temporal behavioursof the proposed neural circuits and illustrate some outstandingfunctional features of the neural model: spike-mediated modulationof the neural activity, self-regulation of the total activityin neural groups, and emulation of temporal interaction mechanismswith well controlled time constants at different scales.
    Materialart: Digitale Medien
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
Schließen ⊗
Diese Webseite nutzt Cookies und das Analyse-Tool Matomo. Weitere Informationen finden Sie hier...