• DocumentCode
    1754029
  • Title

    Multi-degree of Freedom Neurons Geometric Computation Based on Clifford Algebra

  • Author

    Ding, Lijun ; Feng, Hao ; Hua, Liang

  • Author_Institution
    Coll. of Inf. Eng., Zhejiang Univ. of Technol., Hangzhou, China
  • Volume
    1
  • fYear
    2011
  • fDate
    28-29 March 2011
  • Firstpage
    177
  • Lastpage
    180
  • Abstract
    The cognitive algorithm of multi-degree of freedom neurons (MDFNs) was an important implementation method for Bionic Pattern Recognition (BPR), which was computed by high dimensional Euclidean geometrics. This paper proposed a new method for computing the MDFNs based on Clifford algebra, and gave out the corresponding proves to this method. Especially, the computing expressions for Clifford distant between a point and a multi-dimensional simplexes in the Clifford space. Comparing to that of being in high dimensional Euclidean geometrics space, the Clifford algebra-based method was more reducing the computational complexity of MDFNs, and was independent of coordinate.
  • Keywords
    algebra; computational complexity; geometry; pattern recognition; Clifford algebra-based method; Euclidean geometrics; bionic pattern recognition; computational complexity reduction; multidegree-of-freedom neurons geometric computation; statistical learning theory; structural risk minimization; support vector machine model; Algebra; Biological system modeling; Business process re-engineering; Mathematical model; Neurons; Pattern recognition; Support vector machines; Biomic Pattern Recognition; Clifford Algebra; Multi-degree of Freedom; Neuron Computation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Computation Technology and Automation (ICICTA), 2011 International Conference on
  • Conference_Location
    Shenzhen, Guangdong
  • Print_ISBN
    978-1-61284-289-9
  • Type

    conf

  • DOI
    10.1109/ICICTA.2011.53
  • Filename
    5750585