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.
Department, Program, or Center
Chester F. Carlson Center for Imaging Science (COS)
Peter G. Anderson. The Unit RBF network: Experiments and preliminary results. Cybernetics and Systems, 33, 4, 379-390, Nov 2010.
RIT – Main Campus