• DocumentCode
    1951133
  • Title

    Theories of Neural Networks Leading to Unsupervised Learning

  • Author

    Szu, Harold

  • Author_Institution
    Fellows of AIMBE, IEEE, OSA, SPIE; ONR & GWU, szuh@onr.navy.mil; szuh@gwu.edu
  • fYear
    2007
  • fDate
    12-17 Aug. 2007
  • Firstpage
    3116
  • Lastpage
    3123
  • Abstract
    In this paper, we derive an exact single-pixel BSS solution for two components. Furthermore, we prove the solution for n components to be unique and stable by means of the augmented Lagrange or Karush, Kuhn and Tucker methodology [S 07]. Our constant-temperature free energy can estimate the neuronal population of brain´s grey matter which is responsible for the consciousness activities identified by Crick & Koch as the Claustrum accomplishing binding among firing rates (similar to C-node tuning in the beginning of an orchestra performance). Furthermore, the retinal neuronal response Mexican hat functions could be explained by finite resource sharing for replenishment.
  • Keywords
    autoregressive processes; blind source separation; independent component analysis; learning (artificial intelligence); neural nets; time series; Lagrange parameter; Wiener auto-regression; artificial neural network; blind sources separation; brain neural net; independent component analysis; unsupervised learning; vector time series; Animals; Artificial neural networks; Biological neural networks; Blood; Eyes; Independent component analysis; Intelligent sensors; Neural networks; Temperature sensors; Unsupervised learning;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2007. IJCNN 2007. International Joint Conference on
  • Conference_Location
    Orlando, FL
  • ISSN
    1098-7576
  • Print_ISBN
    978-1-4244-1379-9
  • Electronic_ISBN
    1098-7576
  • Type

    conf

  • DOI
    10.1109/IJCNN.2007.4371458
  • Filename
    4371458