The Unit RBF network: experiments and preliminary results

Show full item record

Title: The Unit RBF network: experiments and preliminary results
Author: Anderson, Peter
Abstract: URBF, the unit radial basis function network is an RBF neural network with all second layer weights set to +/- 1. The URBF models functions or physical phenomena by sampling their behaviors at various probe points, and correcting the model, more and more delicately (i.e., using Gaussian functions with ever narrower spread), when discrepancies are discovered. The probe points---input space positions to test and adjust the network---are linear pixel shuffling points, used for their highly uniform sampling property. We demonstrate the network's performance on several examples. It shows its power via good extrapolation behavior: for smooth-boundary discriminations, very few new hidden units need to be added for a large number of probe points.
Description: Also presented at Neural Computing '98. International ICSC / IFAC Symposium. Held at the Technical University: Vienna, Austria: September 1998. Previously published by Taylor & Francis, in Cybernetics and Systems. Link: http://taylorandfrancis.metapress.com/openurl.asp?genre=article&eissn=1087-6553&volume=33&issue=4&spage=379
Record URI: http://hdl.handle.net/1850/3016
Date: 2002-06-01

Files in this item

Files Size Format View
PAndersonArticle06-01-2002.pdf 693.9Kb PDF View/Open

The following license files are associated with this item:

This item appears in the following Collection(s)

Show full item record

Search RIT DML


Advanced Search

Browse