What Size Net Gives Valid Generalization?

@article{Baum1988WhatSN,
  title={What Size Net Gives Valid Generalization?},
  author={Eric B. Baum and David Haussler},
  journal={Neural Computation},
  year={1988},
  volume={1},
  pages={151-160}
}
We address the question of when a network can be expected to generalize from m random training examples chosen from some arbitrary probability distribution, assuming that future test examples are drawn from the same distribution. Among our results are the following bounds on appropriate sample vs. network size. Assume 0 < ∊ 1/8. We show that if m O(W/∊ log N/∊) random examples can be loaded on a feedforward network of linear threshold functions with N nodes and W weights, so that at least a… CONTINUE READING
Highly Influential
This paper has highly influenced 57 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Related Discussions
This paper has been referenced on Twitter 1 time. VIEW TWEETS

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 679 extracted citations

Generalization and Generalizability Measures

IEEE Trans. Knowl. Data Eng. • 1999
View 9 Excerpts
Highly Influenced

Artificial neural networks for computer-based molecular design.

Progress in biophysics and molecular biology • 1998
View 7 Excerpts
Highly Influenced

A Result of Vapnik with Applications

Discrete Applied Mathematics • 1993
View 15 Excerpts
Highly Influenced

Disaggregation-aggregation based model reduction for refinery-wide optimization

Computers & Chemical Engineering • 2011
View 5 Excerpts
Highly Influenced

Generalization Error Bounds for Threshold Decision Lists

Journal of Machine Learning Research • 2004
View 10 Excerpts
Highly Influenced

References

Publications referenced by this paper.
Showing 1-10 of 17 references

Estimation of Dependences Based on Empirical Data

V. N. Vapnik
New York Springer Verlag. • 1982
View 6 Excerpts
Highly Influenced

Connectionist Learning Procedures

Artif. Intell. • 1989
View 2 Excerpts

Automatic Pattern Recognition: A Study of the Probability of Error

IEEE Trans. Pattern Anal. Mach. Intell. • 1988
View 3 Excerpts

On the Capabilities of Multilayer Perceptrons

E. B. Baum
J. of Complexity, • 1988
View 2 Excerpts

Automatic Learning, Rule Extraction, and Generalization

J., D. Schwartz, +4 authors L. Jackel.
Complex Systems 1, 877-922. • 1987

Similar Papers

Loading similar papers…