• DocumentCode
    1748941
  • Title

    Bayesian Ying-Yang harmony learning, information theory and information geometry

  • Author

    Xu, Lei

  • Author_Institution
    Dept. of Comput. Sci., Chinese Univ. of Hong Kong, Shatin, China
  • Volume
    4
  • fYear
    2001
  • fDate
    2001
  • Firstpage
    2744
  • Abstract
    Learning tasks are viewed from the fundamental relationships among the observed data. The key issues of Bayesian Ying Yang system and harmony learning theory are summarized from a systematical perspective. Further discussions are made on its relations to maximum likelihood learning, information theory, information geometry and Helmholtz machine learning
  • Keywords
    Bayes methods; learning (artificial intelligence); maximum likelihood estimation; neural nets; Bayesian Ying-Yang harmony learning; Helmholtz machine learning; information geometry; information theory; maximum likelihood learning; neural nets; Bayesian methods; Computer science; Covariance matrix; Information geometry; Information theory; Lattices; Machine learning; Maximum likelihood estimation; Stochastic processes; Topology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
  • Conference_Location
    Washington, DC
  • ISSN
    1098-7576
  • Print_ISBN
    0-7803-7044-9
  • Type

    conf

  • DOI
    10.1109/IJCNN.2001.938807
  • Filename
    938807
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1748941