Smoothing Regularizers for Projective Basis Function Networks
Abstract
Smoothing regularizers for radial basis functions have been studied extensively, but no general smoothing regularizers for projective basis junctions (PBFs), such as the widely-used sigmoidal PBFs, have heretofore been proposed. We de(cid:173) rive new classes of algebraically-simple mH'-order smoothing regularizers for networks of the form f(W, x) = L7=1 Ujg [x T Vj + Vjol + uo, with general projective basis functions g[.]. These regularizers are:
Cite
Text
Moody and Rögnvaldsson. "Smoothing Regularizers for Projective Basis Function Networks." Neural Information Processing Systems, 1996.Markdown
[Moody and Rögnvaldsson. "Smoothing Regularizers for Projective Basis Function Networks." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/moody1996neurips-smoothing/)BibTeX
@inproceedings{moody1996neurips-smoothing,
title = {{Smoothing Regularizers for Projective Basis Function Networks}},
author = {Moody, John E. and Rögnvaldsson, Thorsteinn S.},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {585-591},
url = {https://mlanthology.org/neurips/1996/moody1996neurips-smoothing/}
}