355 search results - page 49 / 71 » Online Learning and Exploiting Relational Models in Reinforc... |
IJCAI
2007
14 years 11 months ago
2007
A key problem in reinforcement learning is finding a good balance between the need to explore the environment and the need to gain rewards by exploiting existing knowledge. Much ...
140
click to vote
CVPR
2012
IEEE
13 years 4 days ago
2012
IEEE
In this paper we introduce Structured Local Predictors (SLP) – A new formulation that considers the image labelling problem from a structured learning point of view. SLP are loc...
ICCV
2011
IEEE
13 years 9 months ago
2011
IEEE
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
95
Voted
KDD
2008
ACM
15 years 10 months ago
2008
ACM
A hypergraph is a generalization of the traditional graph in which the edges are arbitrary non-empty subsets of the vertex set. It has been applied successfully to capture highord...
ICWE
2004
Springer
15 years 3 months ago
2004
Springer
Abstract. In recent years, more and more publications and material for studying and teaching, e. g. for Web-based teaching (WBT), appear "online" and digital libraries ar...