Sciweavers

603 search results - page 23 / 121
» A theory of learning from different domains
Sort
View
COOPIS
2004
IEEE
15 years 9 months ago
Learning Classifiers from Semantically Heterogeneous Data
Semantically heterogeneous and distributed data sources are quite common in several application domains such as bioinformatics and security informatics. In such a setting, each dat...
Doina Caragea, Jyotishman Pathak, Vasant Honavar
ACL
2010
15 years 4 months ago
Open-Domain Semantic Role Labeling by Modeling Word Spans
Most supervised language processing systems show a significant drop-off in performance when they are tested on text that comes from a domain significantly different from the domai...
Fei Huang, Alexander Yates
ECCV
2006
Springer
16 years 8 months ago
A Theory of Spherical Harmonic Identities for BRDF/Lighting Transfer and Image Consistency
Abstract. We develop new mathematical results based on the spherical harmonic convolution framework for reflection from a curved surface. We derive novel identities, which are the ...
Dhruv Mahajan, Ravi Ramamoorthi, Brian Curless
IADIS
2004
15 years 7 months ago
Electronic case studies: a problem-based learning approach
E-Cases is an innovative approach to management development. Traditional case studies typically describe a decision or a problem in a real-life setting. E-Cases encourage students...
Philip M. Drinkwater, Christopher P. Holland, K. N...
AGENTS
2001
Springer
15 years 10 months ago
Using background knowledge to speed reinforcement learning in physical agents
This paper describes Icarus, an agent architecture that embeds a hierarchical reinforcement learning algorithm within a language for specifying agent behavior. An Icarus program e...
Daniel G. Shapiro, Pat Langley, Ross D. Shachter