Annealed theories of learning (1995) [13 citations — 2 self]
by H. S. Seung
In J.-H
http://hebb.mit.edu/people/seung/papers/annealed.ps.gz
Add To MetaCart
Popular Tags
No tags have been applied to this document.
BibTeX | Add To MetaCart
@INPROCEEDINGS{Seung95annealedtheories,author = {H. S. Seung},
title = {Annealed theories of learning},
booktitle = {In J.-H},
year = {1995},
pages = {32--41},
publisher = {World Scientific}
}
Years of Citing Articles
Abstract:
We study annealed theories of learning boolean functions using a concept class of finite cardinality. The naive annealed theory can be used to derive a universal learning curve bound for zero temperature learning, similar to the inverse square root bound from the Vapnik-Chervonenkis theory. Tighter, nonuniversal learning curve bounds are also derived. A more refined annealed theory leads to still tighter bounds, which in some cases are very similar to results previously obtained using one-step replica symmetry breaking.
Citations
| 637 | Estinwtion of Dependences Based on Empirical Data – Vapnik - 1982 |
| 56 | Rigorous learning curve bounds from statistical mechanics – Haussler, Kearns, et al. - 1996 |
| 43 | Statistical mechanics of learning from examples – Seung, Sompolinsky, et al. - 1992 |
| 25 | Statistical theory of learning a rule – Gyorgyi, Tishby - 1990 |
| 21 | Four types of lea.rning curves – Amari, Fujita, et al. - 1992 |
| 20 | Exhaustive learning – Schwartz, Samalam, et al. - 1990 |
| 5 | den Broeck. Systems that can learn from examples: replica calculation of uniform convergence bounds for the perceptron – Engel, van - 1993 |
| 4 | Generalization in a two-layer neural network – Kang, Oh, et al. - 1993 |
| 3 | Generalization in fully connected committee machines – Schwarze, Hertz - 1993 |
| 2 | Learning curves for error minimum and maximum likelihood algorithms – Kabashima, Shinomoto - 1992 |
