Sciweavers

4366 search results - page 334 / 874
» Learning and Smoothed Analysis
Sort
View
PR
2006
101views more  PR 2006»
15 years 6 months ago
Feature-based approach to semi-supervised similarity learning
For the management of digital document collections, automatic database analysis still has ties to deal with semantic queries and abstract concepts that users are looking for. When...
Philippe Henri Gosselin, Matthieu Cord
IJCSA
2007
104views more  IJCSA 2007»
15 years 6 months ago
Solving the Satisfiability Problem Using Finite Learning Automata
A large number of problems that occur in knowledge-representation, learning, VLSI-design, and other areas of artificial intelligence, are essentially satisfiability problems. The ...
Ole-Christoffer Granmo, Noureddine Bouhmala
ML
2002
ACM
168views Machine Learning» more  ML 2002»
15 years 6 months ago
On Average Versus Discounted Reward Temporal-Difference Learning
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
John N. Tsitsiklis, Benjamin Van Roy
PR
2007
139views more  PR 2007»
15 years 6 months ago
Learning the kernel matrix by maximizing a KFD-based class separability criterion
The advantage of a kernel method often depends critically on a proper choice of the kernel function. A promising approach is to learn the kernel from data automatically. In this p...
Dit-Yan Yeung, Hong Chang, Guang Dai
NECO
2010
97views more  NECO 2010»
15 years 5 months ago
Rademacher Chaos Complexities for Learning the Kernel Problem
In this paper we develop a novel generalization bound for learning the kernel problem. First, we show that the generalization analysis of the kernel learning problem reduces to in...
Yiming Ying, Colin Campbell