Smoothing Regularizers for Projective Basis Function Networks
Moody, John E., Rögnvaldsson, Thorsteinn S.
–Neural Information Processing Systems
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 derive newclasses of algebraically-simple mH'-order smoothing regularizers for networks of the form f(W, x)
Neural Information Processing Systems
Dec-31-1997