Sciweavers

COLT
1994
Springer
13 years 8 months ago
Learning Probabilistic Automata with Variable Memory Length
We propose and analyze a distribution learning algorithm for variable memory length Markov processes. These processes can be described by a subclass of probabilistic nite automata...
Dana Ron, Yoram Singer, Naftali Tishby
COLT
1994
Springer
13 years 8 months ago
Bayesian Inductive Logic Programming
Inductive Logic Programming (ILP) involves the construction of first-order definite clause theories from examples and background knowledge. Unlike both traditional Machine Learnin...
Stephen Muggleton
COLT
1994
Springer
13 years 8 months ago
Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes
We examine the relationship between the VCdimension and the number of parameters of a smoothly parametrized function class. We show that the VC-dimension of such a function class ...
Wee Sun Lee, Peter L. Bartlett, Robert C. Williams...
COLT
1994
Springer
13 years 8 months ago
Playing the Matching-Shoulders Lob-Pass Game with Logarithmic Regret
The best previous algorithmfor the matching shoulders lob-pass game, Abe and Takeuchi's (1993)ARTHUR, suffered O(t1
Joe Kilian, Kevin J. Lang, Barak A. Pearlmutter
COLT
1994
Springer
13 years 8 months ago
Rigorous Learning Curve Bounds from Statistical Mechanics
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 ...
David Haussler, H. Sebastian Seung, Michael J. Kea...
COLT
1994
Springer
13 years 8 months ago
Efficient Reinforcement Learning
Realistic domains for learning possess regularities that make it possible to generalize experience across related states. This paper explores an environment-modeling framework tha...
Claude-Nicolas Fiechter
COLT
1994
Springer
13 years 8 months ago
Fat-Shattering and the Learnability of Real-Valued Functions
Peter L. Bartlett, Philip M. Long, Robert C. Willi...
COLT
1994
Springer
13 years 8 months ago
An Optimal Parallel Algorithm for Learning DFA
: Sequential algorithms given by Angluin 1987 and Schapire 1992 learn deterministic nite automata DFA exactly from Membership and Equivalence queries. These algorithms are feasible...
José L. Balcázar, Josep Díaz,...