Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

April 1, 1996, Vol. 8, No. 3, Pages 595-609
(doi: 10.1162/neco.1996.8.3.595)
© 1996 Massachusetts Institute of Technology
Minimum Description Length, Regularization, and Multimodal Data
Article PDF (757.51 KB)
Abstract

Relationships between clustering, description length, and regularization are pointed out, motivating the introduction of a cost function with a description length interpretation and the unusual and useful property of having its minimum approximated by the densest mode of a distribution. A simple inverse kinematics example is used to demonstrate that this property can be used to select and learn one branch of a multivalued mapping. This property is also used to develop a method for setting regularization parameters according to the scale on which structure is exhibited in the training data. The regularization technique is demonstrated on two real data sets, a classification problem and a regression problem.