Decision theoretic generalizations of the PAC model for neural net and other learning applications (Q1198550)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 89992
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Decision theoretic generalizations of the PAC model for neural net and other learning applications |
scientific article; zbMATH DE number 89992 |
Statements
Decision theoretic generalizations of the PAC model for neural net and other learning applications (English)
0 references
16 January 1993
0 references
The paper introduces an extension of the probably approximately correct model of learing from examples. The class of functions on an instance space that usually are defined only on the set \(\{0,1\}\) has been changed so that values are members of arbitrary sets. The new extended model is based on statistical decision theory. The results of the paper are based on a proposed generalized notion of dimension of Vapnik-Chervonenkis that is applicable to real-valued functions. Due to the extended model, it is possible to formulate distribution-independent upper bounds on the size of the instance space for learning in feed-forward neural networks.
0 references
PAC learning
0 references
Vapnik-Chervonenkis dimension
0 references
neural networks
0 references
0 references
0 references
0.817781388759613
0 references
0.7985556721687317
0 references
