We had previously shown that regularization principles lead to approximation schemes, as Radial Basis Functions, which are equivalent to networks with one layer of hidden units, called Regularization Networks. In this paper we show that regularization networks encompass a much broader range of approximation schemes, including many of the popular general additive models, Breiman's hinge functions and some forms of Projection Pursuit Regression. In the probabilistic interpretation of regularization, the different classes of basis functions correspond to different classes of prior probabilities on the approximating function spaces, and therefore to different types of smoothness assumptions. In the final part of the paper, we also show a relation between activation functions of the Gaussian and sigmoidal type.
Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7212 |
Date | 01 June 1993 |
Creators | Girosi, Federico, Jones, Michael, Poggio, Tomaso |
Source Sets | M.I.T. Theses and Dissertation |
Language | en_US |
Detected Language | English |
Format | 27 p., 768627 bytes, 2437996 bytes, application/octet-stream, application/pdf |
Relation | AIM-1430, CBCL-075 |
Page generated in 0.0012 seconds