8 search results - page 1 / 2 » Rigorous Learning Curve Bounds from Statistical Mechanics |
COLT
1994
Springer
13 years 9 months ago
1994
Springer
In this paper we introduce and investigate a mathematically rigorous theory of learning curves that is based on ideas from statistical mechanics. The advantage of our theory over ...
ML
1998
ACM
13 years 4 months ago
1998
ACM
We review the application of statistical mechanics methods to the study of online learning of a drifting concept in the limit of large systems. The model where a feed-forward netwo...
COLT
2000
Springer
13 years 9 months ago
2000
Springer
Haussler, Kearns, Seung and Tishby introduced the notion of a shell decomposition of the union bound as a means of understanding certain empirical phenomena in learning curves suc...
ML
2010
ACM
12 years 11 months ago
2010
ACM
We introduce a general-purpose learning machine that we call the Guaranteed Error Machine, or GEM, and two learning algorithms, a real GEM algorithm and an ideal GEM algorithm. Th...
IJCNN
2006
IEEE
13 years 11 months ago
2006
IEEE
— It is difficult to map many existing learning algorithms onto biological networks because the former require a separate learning network. The computational basis of biological...