Title page for etd-0727101-134305


[Back to Results | New Search]

URN etd-0727101-134305
Author Chen-Lia Lin
Author's Email Address allensowhat@kimo.com.tw
Statistics This thesis had been viewed 5366 times. Download 3871 times.
Department Mechanical Engineering
Year 2000
Semester 2
Degree Master
Type of Document
Language zh-TW.Big5 Chinese
Title Improving the Generalization Capability
of the RBF Neural Networks
via the Use of Linear Regression Techniques
Date of Defense 2001-06-29
Page Count 63
Keyword
  • Function Approximation
  • Generalization Capability
  • RBF
  • Abstract Neural networks can be looked as a kind of intruments which is
    able to learn. For making the fruitful results of neural networks'
    learning possess parctical applied value, the thesis makes use of
    linear regression technics to strengthen the extended capability of
    RBF neural networks.
       The thesis researches the training methods of RBF neural networks,
    and retains the frame of OLS(orthogonal least square) learning rules
    which is published by Chen and Billings in 1992. Besides, aiming at
    the RBF's characteristics, the thesis brings up improved learning rules
    in first and second phases, and uses " early stop" to be the condition
    of training ceasing.
       To sum up, chiefly the thesis applies some technics of statistic
    linear regression to strenthen the extended capability of RBF, and
    using different methods to do computer simulation in different noise
    situations.
    Advisory Committee
  • Innchyn Her - chair
  • Gou-Jen Wang - co-chair
  • CHEN-WEN YEN - advisor
  • Files
  • etd-0727101-134305.pdf
  • indicate access worldwide
    Date of Submission 2001-07-27

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys