• DocumentCode
    259530
  • Title

    The Two-Stage Analog Neural Network Model and Hardware Implementation

  • Author

    Kawaguchi, Masashi ; Umeno, Masayoshi ; Ishii, Naohiro

  • Author_Institution
    Dept. of Electr. & Electron. Eng., Suzuka Nat. Coll. of Technol., Suzuka, Japan
  • fYear
    2014
  • fDate
    Aug. 31 2014-Sept. 4 2014
  • Firstpage
    936
  • Lastpage
    941
  • Abstract
    In the neural network field, many application models have been proposed. A neuro chip and an artificial retina chip are developed to comprise the neural network model and simulate the biomedical vision system. Previous analog neural network models were composed of the operational amplifier and fixed resistance. It is difficult to change the connection coefficient. In this study, we used analog electronic multiple and sample hold circuits. The connecting weights describe the input voltage. It is easy to change the connection coefficient. This model works only on analog electronic circuits. It can finish the learning process in a very short time and this model will enable more flexible learning.
  • Keywords
    neural nets; sample and hold circuits; analog electronic circuits; analog electronic multiple circuit; artificial retina chip; biomedical vision system simulation; hardware implementation; learning process; neuro chip; sample hold circuit; two-stage analog neural network model; Biological neural networks; Biological system modeling; Integrated circuit modeling; Joining processes; Neurons; SPICE; Solid modeling; electronic circuit; multiple circuit; neural network;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Advanced Applied Informatics (IIAIAAI), 2014 IIAI 3rd International Conference on
  • Conference_Location
    Kitakyushu
  • Print_ISBN
    978-1-4799-4174-2
  • Type

    conf

  • DOI
    10.1109/IIAI-AAI.2014.184
  • Filename
    6913428