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 point - 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.
[1]
Peter G. Anderson,et al.
Advances in Linear Pixel Shuffling
,
1996
.
[2]
Ming Ge,et al.
Using quasirandom numbers in neural networks
,
1995
.
[3]
M. V. Wilkes,et al.
The Art of Computer Programming, Volume 3, Sorting and Searching
,
1974
.
[4]
John Mark,et al.
Introduction to radial basis function networks
,
1996
.
[5]
Peter G. Anderson,et al.
Multidimensional Golden Means
,
1993
.
[6]
Peter G. Anderson,et al.
The Polynomial Method Augmented by Supervised Training for Hand-Printed Character Recognition
,
1993
.
[7]
Christian Lebiere,et al.
The Cascade-Correlation Learning Architecture
,
1989,
NIPS.