Theory of Disagreement-Based Active Learning

1. Auflage 2014
ISBN: 978-1-60198-808-9
Verlag: Now Publishers

Buch, Englisch, Band 22, 194 Seiten, Format (B × H): 156 mm x 234 mm

Reihe: Foundations and Trends® in Machine Learning

Theory of Disagreement-Based Active Learning describes recent advances in our understanding of the theoretical benefits of active learning, and implications for the design of effective active learning algorithms. It is intended for researchers and advanced graduate students in machine learning and statistics who are interested in gaining a deeper understanding of the recent and ongoing developments in the theory of active learning.

Autoren/Hrsg.

Hanneke, Steve

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen

Inhaltsverzeichnis

1. Introduction
2. Basic Definitions and Notation
3. A Brief Review of Passive Learning
4. Lower Bounds on the Label Complexity
5. Disagreement-Based Active Learning
6. Computational Efficiency via Surrogate Losses
7. Bounding the Disagreement Coefficient
8. A Survey of Other Topics and Techniques
References