| Alternate document: Details Learning Switching Concepts (92) Avrim Blum School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 avrim@theory.cs. |
(Enter summary)
Abstract: This paper presents a theoretical model for learning Boolean functions in domains having a
large, potentially infinite number of attributes. The model allows an algorithm to employ a rich
vocabulary to describe the objects it encounters in the world without necessarily incurring time
and space penalties so long as each individual object is relatively simple. We show that many
of the basic Boolean functions learnable in standard theoretical models, such as conjunctions,
disjunctions, K-CNF, ... (Update)
Context of citations to this paper: More
...on n. We note that in the infinite attribute model of Blum, it is possible to have algorithms whose time complexity is sublinear in n [5]. However, we do not consider that model here. If there exists a polynomial time mistake bound algorithm for learning C that makes at...
Cited by: More
Toward Attribute Efficient Learning of Decision Lists and.. - Klivans, Servedio (2006)
(Correct)
Learning with Feature Description Logics - Chad Cumby And (2002)
(Correct)
Learning in the Presence of Finitely or Infinitely.. - Blum, Hellerstein.. (1995)
(Correct)
Similar documents based on text:
92.0: Unknown -
(Correct)
Related documents from co-citation: More All
29: Learning quickly when irrelevant attributes abound: A new linearthreshold algori.. (context) - Littlestone - 1988
17: Learning in the presence of finitely or infinitely many irrelevant attributes
- Blum, Hellerstein et al. - 1995
15: Queries and concept learning (context) - Angluin - 1988
BibTeX entry: (Update)
A. Blum. Learning boolean functions in an infinite attribute space. Machine Learning, 9:373--386, 1992. http://citeseer.ist.psu.edu/blum92learning.html More
@inproceedings{ blum90learning,
author = "A. Blum",
title = "Learning boolean functions in an infinite attribute space",
pages = "64--72",
year = "1990",
url = "citeseer.ist.psu.edu/blum92learning.html" }
Citations not processed or no citations identified.
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.cs.cmu.edu/~avrim/Papers/pubs.html): More
Linear Approximation of Shortest Superstrings - Blum, Jiang, Li, Tromp.. (1991)
(Correct)
Universal Portfolios With and Without Transaction Costs - Blum, Kalai (1997)
(Correct)
A Constant-factor Approximation Algorithm for the k-MST Problem - Blum, Ravi, Vempala (1996)
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC