Sciweavers

377 search results - page 5 / 76
» A Value Theory of Meta-Learning Algorithms
Sort
View
83
Voted
RSA
2002
99views more  RSA 2002»
14 years 9 months ago
Distributed algorithms with dynamical random transitions
Given any measure-preserving dynamical system (Y, A , , T) and g Lp() , we study convergence of the sequence 1 n n k=1 g TSk , n 1 where Sk is a dynamic Zr -valued random w...
Nadine Guillotin-Plantard, René Schott
ENTCS
2008
89views more  ENTCS 2008»
14 years 9 months ago
CC(X): Semantic Combination of Congruence Closure with Solvable Theories
We present a generic congruence closure algorithm for deciding ground formulas in the combination of the theory of equality with uninterpreted symbols and an arbitrary built-in so...
Sylvain Conchon, Evelyne Contejean, Johannes Kanig...
77
Voted
IRI
2005
IEEE
15 years 3 months ago
Handling missing values via decomposition of the conditioned set
In this paper, a framework for replacing missing values in a database is proposed since a real-world database is seldom complete. Good data quality in a database can directly impr...
Mei-Ling Shyu, Indika Kuruppu-Appuhamilage, Shu-Ch...
AAAI
2006
14 years 11 months ago
Value-Function-Based Transfer for Reinforcement Learning Using Structure Mapping
Transfer learning concerns applying knowledge learned in one task (the source) to improve learning another related task (the target). In this paper, we use structure mapping, a ps...
Yaxin Liu, Peter Stone
MFCS
2004
Springer
15 years 2 months ago
The Bidimensional Theory of Bounded-Genus Graphs
Abstract. Bidimensionality provides a tool for developing subexponential fixed-parameter algorithms for combinatorial optimization problems on graph families that exclude a minor....
Erik D. Demaine, Mohammad Taghi Hajiaghayi, Dimitr...