A VLSI-design of the minimum entropy neuron

One of the most interesting domains of feedforward networks is the processing of sensor signals. There do exist some networks which extract most of the information by implementing the maximum entropy principle for Gaussi
One of the most interesting domains of feedforward networks is the processing of sensor signals. There do exist some networks which extract most of the information by implementing the maximum entropy principle for Gaussian sources. This is done by transforming input patterns to the base of eigenvectors of the input autocorrelation matrix with the biggest eigenvalues. The basic building block of these networks is the linear neuron, learning with the Oja learning rule. Nevertheless, some researchers in pattern recognition theory claim that for pattern recognition and classification clustering transformations are needed which reduce the intra-class entropy. This leads to stable, reliable features and is implemented for Gaussian sources by a linear transformation using the eigenvectors with the smallest eigenvalues. In another paper (Brause 1992) it is shown that the basic building block for such a transformation can be implemented by a linear neuron using an Anti-Hebb rule and restricted weights. This paper shows the analog VLSI design for such a building block, using standard modules of multiplication and addition. The most tedious problem in this VLSI-application is the design of an analog vector normalization circuitry. It can be shown that the standard approaches of weight summation will not give the convergence to the eigenvectors for a proper feature transformation. To avoid this problem, our design differs significantly from the standard approaches by computing the real Euclidean norm. Keywords: minimum entropy, principal component analysis, VLSI, neural networks, surface approximation, cluster transformation, weight normalization circuit.
show moreshow less

Download full text files

Export metadata

  • Export Bibtex
  • Export RIS

Additional Services

    Share in Twitter Search Google Scholar
Metadaten
Author:Rüdiger W. Brause
URN:urn:nbn:de:hebis:30-79030
Document Type:Part of a Book
Language:English
Date of Publication (online):2010/09/08
Year of first Publication:1994
Publishing Institution:Univ.-Bibliothek Frankfurt am Main
Release Date:2010/09/08
Tag:VLSI ; cluster transformation; minimum entropy ; neural networks ; principal component analysis ; surface approximation
Source:in: J. Delgado-Frias, W. Moore (eds.): VLSI for artificial intelligence and neural networks, pp. 53-60, Plenum Press, New York, 1994
HeBIS PPN:227572483
Institutes:Informatik
Dewey Decimal Classification:004 Datenverarbeitung; Informatik
Sammlungen:Universitätspublikationen
Licence (German):License Logo Veröffentlichungsvertrag für Publikationen

$Rev: 11761 $