The informational complexity of learning from examples

  title={The informational complexity of learning from examples},
  author={Partha Niyogi},
This thesis attempts to quantify the amount of information needed to learn certain tasks. The tasks chosen vary from learning functions in a Sobolev space using radial basis function networks to learning grammars in the principles and parameters framework of modern linguistic theory. These problems are analyzed from the perspective of computational learning theory and certain unifying perspectives emerge. Copyright c Massachusetts Institute of Technology, 1996 This report describes research… CONTINUE READING
Highly Cited
This paper has 52 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 15 extracted citations

52 Citations

Citations per Year
Semantic Scholar estimates that this publication has 52 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 118 references

How to Set Parameters

View 5 Excerpts
Highly Influenced

Introduction to Government and Binding Theory

Liliane Haegeman
View 6 Excerpts
Highly Influenced

A Theory of the Learnable

STOC • 1984
View 6 Excerpts
Highly Influenced


E. Gibson, K. Wexler
Linguistic Inquiry, 25 • 1994
View 7 Excerpts
Highly Influenced

Universal approximation bounds for superpositions of a sigmoidal function

IEEE Trans. Information Theory • 1993
View 19 Excerpts
Highly Influenced

A simple lemma on greedy approximation in Hilbert space and con- vergence rates for Projection Pursuit Regression and neural network training

L. K. Jones
The Annals of Statistics, • 1992
View 11 Excerpts
Highly Influenced

Approximation and Estimation Bounds for Artificial Neural Networks

Machine Learning • 1991
View 18 Excerpts
Highly Influenced

Real analysis and probability

R. M. Dudley
Mathematics Series. Wadsworth and Brooks/Cole, Paci c Grove, CA • 1989
View 8 Excerpts
Highly Influenced


V. N. Vapnik, A. Ya
The necessary and su cient condi- tions for the uniform convergence of averages to their expected values. Teoriya Veroyatnostei i Ee Primeneniya, 26(3):543{564 • 1981
View 23 Excerpts
Highly Influenced