Sciweavers

JMLR
2002
138views more  JMLR 2002»
13 years 10 months ago
Text Chunking based on a Generalization of Winnow
This paper describes a text chunking system based on a generalization of the Winnow algorithm. We propose a general statistical model for text chunking which we then convert into ...
Tong Zhang, Fred Damerau, David Johnson
JMLR
2002
135views more  JMLR 2002»
13 years 10 months ago
Covering Number Bounds of Certain Regularized Linear Function Classes
Recently, sample complexity bounds have been derived for problems involving linear functions such as neural networks and support vector machines. In many of these theoretical stud...
Tong Zhang
JMLR
2002
100views more  JMLR 2002»
13 years 10 months ago
On the Convergence of Optimistic Policy Iteration
We consider a finite-state Markov decision problem and establish the convergence of a special case of optimistic policy iteration that involves Monte Carlo estimation of Q-values,...
John N. Tsitsiklis
JMLR
2002
79views more  JMLR 2002»
13 years 10 months ago
MDPs: Learning in Varying Environments
Istvan Szita, Bálint Takács, Andr&aa...
JMLR
2002
137views more  JMLR 2002»
13 years 10 months ago
The Subspace Information Criterion for Infinite Dimensional Hypothesis Spaces
A central problem in learning is selection of an appropriate model. This is typically done by estimating the unknown generalization errors of a set of models to be selected from a...
Masashi Sugiyama, Klaus-Robert Müller
JMLR
2002
157views more  JMLR 2002»
13 years 10 months ago
Cluster Ensembles --- A Knowledge Reuse Framework for Combining Multiple Partitions
This paper introduces the problem of combining multiple partitionings of a set of objects into a single consolidated clustering without accessing the features or algorithms that d...
Alexander Strehl, Joydeep Ghosh
JMLR
2002
117views more  JMLR 2002»
13 years 10 months ago
Learning to Construct Fast Signal Processing Implementations
A single signal processing algorithm can be represented by many mathematically equivalent formulas. However, when these formulas are implemented in code and run on real machines, ...
Bryan Singer, Manuela M. Veloso
JMLR
2002
115views more  JMLR 2002»
13 years 10 months ago
PAC-Bayesian Generalisation Error Bounds for Gaussian Process Classification
Approximate Bayesian Gaussian process (GP) classification techniques are powerful nonparametric learning methods, similar in appearance and performance to support vector machines....
Matthias Seeger
JMLR
2002
125views more  JMLR 2002»
13 years 10 months ago
Lyapunov Design for Safe Reinforcement Learning
Lyapunov design methods are used widely in control engineering to design controllers that achieve qualitative objectives, such as stabilizing a system or maintaining a system'...
Theodore J. Perkins, Andrew G. Barto
JMLR
2002
87views more  JMLR 2002»
13 years 10 months ago
Shallow Parsing using Noisy and Non-Stationary Training Material
Shallow parsers are usually assumed to be trained on noise-free material, drawn from the same distribution as the testing material. However, when either the training set is noisy ...
Miles Osborne