Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

ALT
2001
Springer

favoriteEmaildiscussreport

106views Machine Learning» more ALT 2001»

Learning by Switching Type of Information

14 years 1 months ago

Learning by Switching Type of Information

Download www.comp.nus.edu.sg

The present work is dedicated to the study of modes of data-presentation in the range between text and informant within the framework of inductive inference. In this study, the learner alternatingly requests sequences of positive and negative data. We deﬁne various formalizations of valid data presentations in such a scenario. We resolve the relationships between these diﬀerent formalizations, and show that one of these is equivalent to learning from informant. We also show a hierarchy formed (for each of the formalizations studied) by considering the number of switches between requests for positive and negative data.

Sanjay Jain, Frank Stephan

Real-time Traffic

ALT 2001 | Inductive Inference | Machine Learning | Negative Data | Valid Data Presentations |

claim paper

Related Content

» The Inherent Queuing Delay of Parallel Packet Switches

» Automatic Induction of DomainRelated Information Learning Descriptors Type Domains

» Learning SemanticLevel Information Extraction Rules by TypeOriented ILP

» TypeBased Composition of Information Services in Large Scale Environments

» On the Learnability of Vector Spaces

» The Synergy of Learning Organisations and Flexible Information Technology

» A diary study of task switching and interruptions

» A Bayesian Approach for Learning Document Type Relevance

» Improving Offensive Performance Through Opponent Modeling

Post Info
More Details (n/a)

Added	15 Mar 2010
Updated	15 Mar 2010
Type	Conference
Year	2001
Where	ALT
Authors	Sanjay Jain, Frank Stephan

Comments (0)