Sciweavers

74 search results - page 5 / 15
» Imitation learning with generalized task descriptions
Sort
View
AAAI
2008
13 years 9 months ago
Zero-data Learning of New Tasks
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...
Hugo Larochelle, Dumitru Erhan, Yoshua Bengio
WWW
2005
ACM
14 years 8 months ago
Learning domain ontologies for Web service descriptions: an experiment in bioinformatics
The reasoning tasks that can be performed with semantic web service descriptions depend on the quality of the domain ontologies used to create these descriptions. However, buildin...
Marta Sabou, Chris Wroe, Carole A. Goble, Gilad Mi...
PKDD
2009
Springer
174views Data Mining» more  PKDD 2009»
14 years 2 months ago
Active and Semi-supervised Data Domain Description
Data domain description techniques aim at deriving concise descriptions of objects belonging to a category of interest. For instance, the support vector domain description (SVDD) l...
Nico Görnitz, Marius Kloft, Ulf Brefeld
GECCO
2007
Springer
213views Optimization» more  GECCO 2007»
14 years 1 months ago
Genetically programmed learning classifier system description and results
An agent population can be evolved in a complex environment to perform various tasks and optimize its job performance using Learning Classifier System (LCS) technology. Due to the...
Gregory Anthony Harrison, Eric W. Worden
HRI
2006
ACM
14 years 1 months ago
Teaching robots by moulding behavior and scaffolding the environment
Programming robots to carry out useful tasks is both a complex and non-trivial exercise. A simple and intuitive method to allow humans to train and shape robot behaviour is clearl...
Joe Saunders, Chrystopher L. Nehaniv, Kerstin Daut...