Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. Computer Science and Artificial Intelligence Lab (CSAIL)
  3. Artificial Intelligence Lab Publications
  4. AI Memos (1959 - 2004)
  5. Priors Stabilizers and Basis Functions: From Regularization to Radial, Tensor and Additive Splines

Priors Stabilizers and Basis Functions: From Regularization to Radial, Tensor and Additive Splines

Thumbnail Image
Download
Name

AIM-1430.pdf

Size

2.33 MB

Format

Adobe PDF

Checksum (MD5)

3f34a63ae4936b2caafaf3e1c2d84edf

Thumbnail Image
Download
Name

AIM-1430.ps.Z

Size

750.61 KB

Format

Unknown

Checksum (MD5)

4627b59e629760667a9001594fcb754b

Author(s)
Girosi, Federico
•
Jones, Michael
•
Poggio, Tomaso
Date Issued
June 1, 1993
Series/Report no.
AIM-1430
CBCL-075
Abstract
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.
Subjects
regularization theory
radial basis functions
additivesmodels
prior knowledge
multilayer perceptrons
Persistent DSpace Link
http://hdl.handle.net/1721.1/7212
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.