Sciweavers

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

14

AMAI
2004
Springer

favoriteEmaildiscussreport

96views Artificial Intelligence» more AMAI 2004»

Learning via Finitely Many Queries

13 years 10 months ago

Learning via Finitely Many Queries

Download rutcor.rutgers.edu

This work introduces a new query inference model that can access data and communicate with a teacher by asking ﬁnitely many boolean queries in a language L. In this model the parameters of interest are the number of queries used and the expressive power of L. We study how the learning power varies with these parameters. Preliminary results suggest that this model can help studying query inference in an resource bounded environment.

Andrew C. Lee

Real-time Traffic

AMAI 2004 | Artificial Intelligence | Boolean Queries | Learning Power Varies | Query Inference Model |

claim paper

Related Content

» How Many Query Superpositions Are Needed to Learn

» Learning search tasks in queries and web pages via graph regularization

» Generalizing over Several Learning Settings

» Actively Learning Ontology Matching via User Interaction

» Robust ranking models via risksensitive optimization

» Approximating the Expressive Power of Logics in Finite Models

» Recursive Teaching Dimension Learning Complexity and Maximum Classes

» Locality Versus Globality QueryDriven Localized Linear Models for Facial Image Computing

» Write it recursively a generic framework for optimal path queries

Post Info
More Details (n/a)

Added	30 Jun 2010
Updated	30 Jun 2010
Type	Conference
Year	2004
Where	AMAI
Authors	Andrew C. Lee

Comments (0)