2623 search results - page 113 / 525 » Universal Learning Theory |
96
Voted
CIE
2007
Springer
15 years 6 months ago
2007
Springer
In the standard model of inductive inference, a learner gets as input the graph of a function, and has to discover (in the limit) a program for the function. In this paper, we cons...
125
Voted
ICONIP
2008
15 years 2 months ago
2008
A number of learning machines used in information science are not regular, but rather singular, because they are non-identifiable and their Fisher information matrices are singula...
144
Voted
COLT
2001
Springer
15 years 5 months ago
2001
Springer
We prove strong noise-tolerance properties of a potential-based boosting algorithm, similar to MadaBoost (Domingo and Watanabe, 2000) and SmoothBoost (Servedio, 2003). Our analysi...
86
Voted
SIGCSE
1999
ACM
15 years 4 months ago
1999
ACM
A Global Cooperation Project was conducted with computer science classes at the Czech Technical University and North Hennepin Community College. The project was a pilot project fo...
NIPS
2003
15 years 2 months ago
2003
Most machine learning researchers perform quantitative experiments to estimate generalization error and compare algorithm performances. In order to draw statistically convincing c...