Sciweavers

AAAI
2008
13 years 12 months ago
Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation
Off-policy reinforcement learning is aimed at efficiently reusing data samples gathered in the past, which is an essential problem for physically grounded AI as experiments are us...
Hirotaka Hachiya, Takayuki Akiyama, Masashi Sugiya...
AAAI
2008
13 years 12 months ago
Lexical and Grammatical Inference
Children are facile at both discovering word boundaries and using those words to build higher-level structures in tandem. Current research treats lexical acquisition and grammar i...
Tom Armstrong, Tim Oates
AAAI
2007
13 years 12 months ago
Recognition of Hand Drawn Chemical Diagrams
Chemists often use hand-drawn structural diagrams to capture and communicate ideas about organic compounds. However, the software available today for specifying these structures t...
Tom Y. Ouyang, Randall Davis
AAAI
2007
13 years 12 months ago
Single Document Summarization with Document Expansion
Existing methods for single document summarization usually make use of only the information contained in the specified document. This paper proposes the technique of document expa...
Xiaojun Wan, Jianwu Yang
AAAI
2008
13 years 12 months ago
Adapting ADtrees for High Arity Features
ADtrees, a data structure useful for caching sufficient statistics, have been successfully adapted to grow lazily when memory is limited and to update sequentially with an increme...
Robert Van Dam, Irene Langkilde-Geary, Dan Ventura
AAAI
2008
13 years 12 months ago
An Interaction-Based Approach to Computational Epidemiology
Christopher L. Barrett, Stephen Eubank, Madhav V. ...
AAAI
2007
13 years 12 months ago
An Egalitarist Fusion of Incommensurable Ranked Belief Bases under Constraints
In the last decade, several approaches have been proposed for merging multiple and potentially conflicting pieces of information. Egalitarist fusion modes privilege solutions tha...
Salem Benferhat, Sylvain Lagrue, Julien Rossit
AAAI
2007
13 years 12 months ago
Discovering Near Symmetry in Graphs
Symmetry is a widespread phenomenon that can offer opportunities for powerful exploitation in areas as diverse as molecular chemistry, pure mathematics, circuit design, biology an...
Maria Fox, Derek Long, Julie Porteous