AAAI-2008 Paper Digest

Every paper, ordered by impact or potential impact. About AAAI 2008

IDPaperAuthors
1Zero-data Learning Of New Tasks
IF:7   Related Papers   Related Patents   Related Grants   Related Venues   Related Experts   View    Save
Highlight: We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or tasks are provided.
Hugo Larochelle; Dumitru Erhan; Yoshua Bengio;
2Single Document Keyphrase Extraction Using Neighborhood Knowledge
IF:7   Related Papers   Related Patents   Related Grants   Related Venues   Related Experts   View    Save
Highlight: Existing methods for single document keyphrase extraction usually make use of only the information contained in the specified document.
Xiaojun Wan; Jianguo Xiao;
3Trace Ratio Criterion For Feature Selection
IF:6   Related Papers   Related Patents   Related Grants   Related Venues   Related Experts   View    Save
Highlight: In this paper, we directly optimize the subset-level score, and propose a novel algorithm to efficiently find the global optimal feature subset such that the subset-level score is maximized.
Feiping Nie; Feiping Nie; Shiming Xiang et al.
4Simulation-Based Approach To General Game Playing
IF:6   Related Papers   Related Patents   Related Grants   Related Venues   Related Experts   View    Save
Highlight: In this paper we describe a GGP agent that instead uses a Monte Carlo/UCT simulation technique for action selection, an approach recently popularized in computer Go.
Hilmar Finnsson; Yngvi Björnsson;
5Lifted First-Order Belief Propagation
IF:6   Related Papers   Related Patents   Related Grants   Related Venues   Related Experts   View    Save
Highlight: In this paper we propose the first lifted version of a scalable probabilistic inference algorithm, belief propagation (loopy or not).
Parag Singla; Pedro Domingos;

About AAAI 2008