Repository logo
Log In(current)
  1. Home
  2. Colleges & Schools
  3. Graduate School
  4. Masters Theses
  5. Gradient descent training of the middle layer parameters in radial basis function neural networks
Details

Gradient descent training of the middle layer parameters in radial basis function neural networks

Date Issued
December 1994
Author(s)
Saffell, Matthew John, 1970-
Advisor(s)
Bruce Whitehead
Additional Advisor(s)
Dinesh Mehta
Al Pujol
Permanent URI
https://trace.tennessee.edu/handle/20.500.14382/59259
Abstract

Radial basis function neural networks have been gaining popularity in recent years for use in approximating unknown functions. A drawback of using radial basis functions in a neural network is that a certain amount of trial and error goes into choosing the parameters of the basis functions such as the placement and the widths of the functions. Along with the time and effort that is involved, it is unlikely that using trial and error or some heuristic method to generate the parameters will find better than a fair approximation to the best possible values. This thesis discusses the use of gradient descent techniques to modify the basis function parameters during the training of the radial basis network. Using this technique, normalized error rates have been achieved on the Mackey-Glass time series data that compare favorably with other neural network training methods.

 
Degree
Master of Science
Major
Computer Science
File(s)
Thumbnail Image
Name

Thesis94.S331.pdf

Size

1.4 MB

Format

Adobe PDF

Checksum (MD5)

575731d5cf6ace7ab898fabf93d02d2c


University Libraries

1015 Volunteer Boulevard
Knoxville, TN 37996
865-974-4351

Map & Directions
Donate to the Libraries
  • About
  • John C. Hodges Society
  • Speaking Volumes magazine
  • Outreach
  • Directory
  • Employment
  • Policies
  • Library Intranet
University of Tennessee power T logo

The University of Tennessee, Knoxville
Knoxville, Tennessee 37996
865-974-1000

Events
A-Z
Apply
Privacy
Map
Directory
Give to UT
Accessibility

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science