• DocumentCode
    751048
  • Title

    GANGLION-a fast field-programmable gate array implementation of a connectionist classifier

  • Author

    Cox, Charles E. ; Blanz, W. Ekkehard

  • Author_Institution
    IBM Almaden Res. Center, San Jose, CA, USA
  • Volume
    27
  • Issue
    3
  • fYear
    1992
  • fDate
    3/1/1992 12:00:00 AM
  • Firstpage
    288
  • Lastpage
    299
  • Abstract
    71 The architecture, implementation, and application of GANGLION, a totally digital connectionist classifier, are described. This fully interconnected feedforward net with one hidden layer is capable of generating 4.48 billion interconnection/s. The architecture is realized on a single 9U VME card and is built entirely from off-the-shelf components. The very high throughput of 20 million decision/s is achieved by making efficient use of field-programmable gate arrays. Specifically, the authors take advantage of the reprogrammability of the devices to automatically generate new custom hardware for each application of the classifier
  • Keywords
    computerised pattern recognition; logic arrays; neural nets; 9U VME card; GANGLION; artificial neural networks; connectionist classifier; fast FPGA implementation; field-programmable gate array; fully interconnected feedforward net; hidden layer; Algorithm design and analysis; Character recognition; Classification algorithms; Field programmable gate arrays; Hardware; High speed optical techniques; Integrated circuit interconnections; Machine vision; Optical character recognition software; Throughput;
  • fLanguage
    English
  • Journal_Title
    Solid-State Circuits, IEEE Journal of
  • Publisher
    ieee
  • ISSN
    0018-9200
  • Type

    jour

  • DOI
    10.1109/4.121550
  • Filename
    121550