• DocumentCode
    880287
  • Title

    Comments on "Optimal training of thresholded linear correlation classifiers" [with reply]

  • Author

    Lovell, David ; Tsoi, A.C. ; Downs, T. ; Hildebrandt, T.H.

  • Author_Institution
    Dept. of Electr. Eng., Queensland Univ., St. Lucia, Qld., Australia
  • Volume
    4
  • Issue
    2
  • fYear
    1993
  • fDate
    3/1/1993 12:00:00 AM
  • Firstpage
    367
  • Lastpage
    369
  • Abstract
    A difficulty with the application of the closed-form training algorithm for the neocognitron proposed by T.H. Hildebrandt (ibid., vol.2, p.557-88, Nov. 1991) is reported. In applying this algorithm the commenters have observed that S-cells frequently fail to respond to features that they have been trained to extract. Results which indicate that this training vector rejection in an important factor in the overall classification performance of the neocognitron trained using Hildebrandt´s procedure are presented. In reply, Hildebrandt explains that the negative results obtained by the commenter are not specific to the proposed algorithm and are easily explained in terms of set theory.<>
  • Keywords
    learning (artificial intelligence); neural nets; pattern recognition; closed-form training; learning; neocognitron; neural nets; pattern recognition; thresholded linear correlation classifiers; Correlators; Feature extraction; Kernel; Partitioning algorithms; Testing;
  • fLanguage
    English
  • Journal_Title
    Neural Networks, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1045-9227
  • Type

    jour

  • DOI
    10.1109/72.207625
  • Filename
    207625