Sciweavers

54 search results - page 3 / 11
» Learning to Create is as Hard as Learning to Appreciate
Sort
View
FOCS
1990
IEEE
13 years 11 months ago
Separating Distribution-Free and Mistake-Bound Learning Models over the Boolean Domain
Two of the most commonly used models in computational learning theory are the distribution-free model in which examples are chosen from a fixed but arbitrary distribution, and the ...
Avrim Blum
SIGSOFT
2010
ACM
13 years 5 months ago
SCORE: the first student contest on software engineering
The Student Contest on Software Engineering (SCORE), organized for the first time in conjunction with the International Conference on Software Engineering (ICSE) 2009, attracted 5...
Dino Mandrioli, Stephen Fickas, Carlo A. Furia, Me...
AGENTS
1998
Springer
13 years 11 months ago
Learning Situation-Dependent Costs: Improving Planning from Probabilistic Robot Execution
Physical domains are notoriously hard to model completely and correctly, especially to capture the dynamics of the environment. Moreover, since environments change, it is even mor...
Karen Zita Haigh, Manuela M. Veloso
MM
2005
ACM
172views Multimedia» more  MM 2005»
14 years 29 days ago
Learning the semantics of multimedia queries and concepts from a small number of examples
In this paper we unify two supposedly distinct tasks in multimedia retrieval. One task involves answering queries with a few examples. The other involves learning models for seman...
Apostol Natsev, Milind R. Naphade, Jelena Tesic
WSDM
2010
ACM
245views Data Mining» more  WSDM 2010»
14 years 4 months ago
Improving Quality of Training Data for Learning to Rank Using Click-Through Data
In information retrieval, relevance of documents with respect to queries is usually judged by humans, and used in evaluation and/or learning of ranking functions. Previous work ha...
Jingfang Xu, Chuanliang Chen, Gu Xu, Hang Li, Elbi...