Query by committee, linear separation and random walks

Theoretical Computer Science

Volumn 284, Issue 1, 2002, Pages 25-51

  Fine, Shai ^a   Gilad Bachrach, Ran ^a   Shamir, Eli ^a  

^a HEBREW UNIVERSITY OF JERUSALEM   (Israel)

Author keywords

Active learning; Experimental design; Labeled and unlabelled data; Selective sampling; Volume approximation

Indexed keywords

APPROXIMATION THEORY; COMPUTATIONAL COMPLEXITY; COMPUTATIONAL GEOMETRY; LEARNING ALGORITHMS; MONTE CARLO METHODS; PROBLEM SOLVING; RANDOM PROCESSES;

RANDOM WALKS;

LEARNING SYSTEMS;

EID: 0037031027     PISSN: 03043975     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0304-3975(01)00079-2     Document Type: Conference Paper

References (15)

1. Training connectionist networks with queries and selective sampling
2. Committee-based sampling for training probabilistic classifiers
3. A random polynomial time algorithm for approximating the volume of convex bodies
4. Selective sampling using the query by committee algorithm
5. Bounds on the sample complexity of Bayesian learning using information theory and the vc dimension
6. Random walks in a convex body and an improved volume algorithm
7. Some pac-Bayesian theorems
8. A pac analysis of a Bayesian estimator
9. Support vector method for function approximation, regression estimation, and signal processing