Sciweavers

603 search results - page 44 / 121
» A theory of learning from different domains
Sort
View

Publication
233views
13 years 8 months ago
Sparse reward processes
We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained duri...
Christos Dimitrakakis
ACL
2010
14 years 8 months ago
Experiments in Graph-Based Semi-Supervised Learning Methods for Class-Instance Acquisition
Graph-based semi-supervised learning (SSL) algorithms have been successfully used to extract class-instance pairs from large unstructured and structured text collections. However,...
Partha Pratim Talukdar, Fernando Pereira
TREC
2004
14 years 11 months ago
Can We Get A Better Retrieval Function From Machine?
The quality of an information retrieval system heavily depends on its retrieval function, which returns a similarity measurement between the query and each document in the collect...
Weiguo Fan, Wensi Xi, Edward A. Fox, Li Wang
IIE
2007
63views more  IIE 2007»
14 years 10 months ago
Investigation of Q-Learning in the Context of a Virtual Learning Environment
We investigate the possibility to apply a known machine learning algorithm of Q-learning in the domain of a Virtual Learning Environment (VLE). It is important in this problem doma...
Dalia Baziukaite
COGSCI
2010
85views more  COGSCI 2010»
14 years 10 months ago
The Effects of Feature-Label-Order and Their Implications for Symbolic Learning
Symbols enable people to organize and communicate about the world. However, the ways in which symbolic knowledge is learned and then represented in the mind are poorly understood....
Michael Ramscar, Daniel Yarlett, Melody Dye, Katie...