• DocumentCode
    276618
  • Title

    An optoelectronic adaptive resonance unit

  • Author

    Wunsch, Donald C., II ; Caudell, Thomas P. ; Capps, C. David ; Falk, R. Aaron

  • Author_Institution
    Boeing Co., Seattle, WA, USA
  • Volume
    i
  • fYear
    1991
  • fDate
    8-14 Jul 1991
  • Firstpage
    541
  • Abstract
    The authors demonstrate a hardware implementation of the adaptive resonance theory ART 1 neural network architecture. The optoelectronic ART1 unit, is a novel application of an old device. This device-the 4-f or Van der Lugt correlator-has historically been used as a fast pattern classifier. Usually the correlation operation is employed as a matched filter, so that a maximum correlation peak corresponds to a well-matched pattern. The device described also uses the large peaks, but takes specific advantage of the fact that a zero-shift correlation is mathematically equivalent to a two-dimensional inner product. The authors describe a promising method for emulating an ART1 unit in optics. They review ART1 from an algorithmic point of view, which shows that inner products are a critical part of ART1. They then discuss its implementation, and show some experimental results. The device works by performing the most computationally intensive parts of the algorithm in optical hardware, and thus offers a suitable marriage of the strengths of electronics and optics
  • Keywords
    computerised pattern recognition; correlators; neural nets; optical information processing; optoelectronic devices; ART 1; Van der Lugt correlator; adaptive resonance theory; correlation operation; fast pattern classifier; neural network architecture; optical hardware; optoelectronic ART1 unit; optoelectronic adaptive resonance unit; two-dimensional inner product; zero-shift correlation; Correlators; Hardware; Lenses; Optical computing; Optical devices; Optical fiber networks; Optical filters; Optical network units; Resonance; Subspace constraints;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
  • Conference_Location
    Seattle, WA
  • Print_ISBN
    0-7803-0164-1
  • Type

    conf

  • DOI
    10.1109/IJCNN.1991.155236
  • Filename
    155236