|
|
||||||||
Letter |
Bell Laboratories, Lucent Technologies, 600 Mountain Ave., Rm. 2C265, Murray Hill, NJ 07974, U.S.A.
Bell Laboratories, Lucent Technologies, 600 Mountain Ave., Rm. 2C265, Murray Hill, NJ 07974, U.S.A.
Learning Systems Group, California Institute of Technology, MC 13693, Pasadena, CA 91125, U.S.A.
We show that with a uniform prior on models having the same training error, early stopping at some fixed training error above the training error minimum results in an increase in the expected generalization error.
This article has been cited by other articles:
![]() |
A. V. Palumbo, J. C. Schryver, M. W. Fields, C. E. Bagwell, J.-Z. Zhou, T. Yan, X. Liu, and C. C. Brandt Coupling of Functional Gene Diversity and Geochemical Data from Environmental Samples Appl. Envir. Microbiol., November 1, 2004; 70(11): 6525 - 6534. [Abstract] [Full Text] [PDF] |
||||
![]() |
Z. Chen and S. Haykin On Different Facets of Regularization Theory Neural Comput., December 1, 2002; 14(12): 2791 - 2846. [Abstract] [Full Text] |
||||
![]() |
T. Karkkainen MLP in Layer-Wise Form with Applications to Weight Decay Neural Comput., June 1, 2002; 14(6): 1451 - 1480. [Abstract] [Full Text] |
||||
![]() |
M. Magdon-Ismail No Free Lunch for Noise Prediction Neural Comput., March 1, 2000; 12(3): 547 - 564. [Abstract] [Full Text] |
||||
| HOME | HELP | FEEDBACK | SUBSCRIPTIONS | ARCHIVE | SEARCH | TABLE OF CONTENTS |
| J COGNITIVE NEUROSCIENCE | NEURAL COMPUTATION | MIT PRESS JOURNALS |