Sciweavers

17 search results - page 1 / 4
» Structural Risk Minimization Over Data-Dependent Hierarchies
Sort
View
TIT
1998
80views more  TIT 1998»
13 years 4 months ago
Structural Risk Minimization Over Data-Dependent Hierarchies
The paper introduces some generalizations of Vapnik’s method of structural risk minimisation (SRM). As well as making explicit some of the details on SRM, it provides a result t...
John Shawe-Taylor, Peter L. Bartlett, Robert C. Wi...
JMLR
2002
90views more  JMLR 2002»
13 years 4 months ago
Machine Learning with Data Dependent Hypothesis Classes
We extend the VC theory of statistical learning to data dependent spaces of classifiers. This theory can be viewed as a decomposition of classifier design into two components; the...
Adam Cannon, J. Mark Ettinger, Don R. Hush, Clint ...
IFIP
2004
Springer
13 years 10 months ago
Tailoring Recursion to Characterize Non-Deterministic Complexity Classes over Arbitrary Structures
We provide machine-independent characterizations of some complexity classes, over an arbitrary structure, in the model of computation proposed by L. Blum, M. Shub and S. Smale. We ...
Olivier Bournez, Felipe Cucker, Paulin Jacob&eacut...
IANDC
2006
83views more  IANDC 2006»
13 years 4 months ago
Implicit complexity over an arbitrary structure: Quantifier alternations
We provide machine-independent characterizations of some complexity classes, over an arbitrary structure, in the model of computation proposed by L. Blum, M. Shub and S. Smale. We...
Olivier Bournez, Felipe Cucker, Paulin Jacob&eacut...
NAACL
2004
13 years 6 months ago
Minimum Bayes-Risk Decoding for Statistical Machine Translation
We present Minimum Bayes-Risk (MBR) decoding for statistical machine translation. This statistical approach aims to minimize expected loss of translation errors under loss functio...
Shankar Kumar, William J. Byrne