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.

Publication Date



This is an Accepted Manuscript of an article published by Taylor & Francis in Cybernetics and Systems on November 30, 2010, available online: http://www.tandfonline.com/doi/abs/10.1080/01969720290040641

ISSN: 1087-6553

Also presented at Neural Computing '98. International ICSC / IFAC Symposium. Held at the Technical University: Vienna, Austria: September 1998.

Document Type


Department, Program, or Center

Chester F. Carlson Center for Imaging Science (COS)


RIT – Main Campus