Sciweavers

534 search results - page 78 / 107
» Efficient polynomial L-approximations
Sort
View
NIPS
1996
13 years 9 months ago
Combinations of Weak Classifiers
To obtain classification systems with both good generalizat`ion performance and efficiency in space and time, we propose a learning method based on combinations of weak classifiers...
Chuanyi Ji, Sheng Ma
AAAI
1990
13 years 9 months ago
Some Applications of Graph Bandwidth to Constraint Satisfaction Problems
Bandwidth is a fundamental concept in graph theory which has some surprising applications to a class of AI search problems. Graph bandwidth provides a link between the syntactic s...
Ramin Zabih
ATAL
2010
Springer
13 years 8 months ago
PAC-MDP learning with knowledge-based admissible models
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...
Marek Grzes, Daniel Kudenko
CORR
2010
Springer
167views Education» more  CORR 2010»
13 years 7 months ago
Network Flow Algorithms for Structured Sparsity
We consider a class of learning problems that involve a structured sparsityinducing norm defined as the sum of -norms over groups of variables. Whereas a lot of effort has been pu...
Julien Mairal, Rodolphe Jenatton, Guillaume Obozin...
DAM
2010
95views more  DAM 2010»
13 years 7 months ago
Excessive factorizations of bipartite multigraphs
Let G be a multigraph. We say that G is 1-extendable if every edge of G is contained in a 1-factor. Suppose G is 1-extendable. An excessive factorization of G is a set F = {F1, F2...
David Cariolaro, Romeo Rizzi