Dana Angluin, et al.  Home/Search
Context Related
| mit.edu/~slonim/AS94.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: mit.edu/~slonim/incomplete (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: . We introduce a new fault-tolerant model of algorithmic learning using an equivalence oracle and an incomplete membership oracle, in which the answers to a random subset of the learner's membership queries may be missing. We demonstrate that, with high probability, it is still possible to learn monotone DNF formulas in polynomial time, provided that the fraction of missing answers is bounded by some constant less than one. Even when half the membership queries are expected to yield no... (Update)
Context of citations to this paper: More
.... model (e.g. 1, 2, 5, 12, 13, 26, 28, 14, 10, 9] and many others) In some of the above, and in several related papers (e.g. [3, 18, 6, 13, 8, 11, 14, 7]) the following common approach is used: the input space, f0; 1g n , is viewed as a lattice with the natural partial order,...
...classes. In the literature of learning theory, the teacher has been modeled di#erently in various learning frameworks [3, 8, 9, 10, 11, 15, 20, 22, 23], and the impact of teaching depends on how much the teacher is involved in the learning process. We study the importance...
Cited by: More
Active Learning with Multiple Views - Muslea (2002) (Correct)
Learning From Examples With Unspecified Attribute Values - Goldman, Kwek (1997) (Correct)
Malicious Omissions and Errors in Answers to Membership.. - Martins, Sloan.. (1997) (Correct)
Similar documents (at the sentence level):
54.1%: Learning Monotone DNF with an Incomplete Membership Oracle - Dana Angluin (1991) (Correct)
37.4%: Learning from Imperfect Data in Theory and Practice - Slonim (1996) (Correct)
Active bibliography (related documents): More All
0.4: Learning Fallible Deterministic Finite Automata - Ron, al. (1995) (Correct)
0.3: Complexity Theoretic Hardness Results for Query Learning - Aizenstein, Hegedüs.. (1998) (Correct)
0.2: Learning k-term DNF Formulas with an Incomplete Membership.. - Goldman, Mathias (1992) (Correct)
Similar documents based on text: More All
0.3: The Power of Team Exploration: Two Robots Can Learn Unlabeled .. - Bender, Slonim (1995) (Correct)
0.3: Exact Learning of u-DNF Formulas with Malicious Membership Queries - Angluin (1994) (Correct)
0.3: Learning Conjunctions of Horn Clauses - Angluin, Frazier, Pitt (1992) (Correct)
Related documents from co-citation: More All
16: Queries and concept learning (context) - Angluin - 1988
11: Exact learning via the monotone theory (context) - Bshouty - 1995
10: Learning with malicious membership queries and exceptions (context) - Angluin, Krikis - 1994
BibTeX entry: (Update)
Angluin, D. and Slonim, D. K. 1994. Randomly fallible teachers: Learning monotone DNF with an incomplete membership oracle. Machine Learning 19, 7--126. http://citeseer.ist.psu.edu/angluin94randomly.html More
@article{ angluin94randomly,
author = "Dana Angluin and Donna K. Slonim",
title = "Randomly Fallible Teachers: Learning Monotone {DNF} with an Incomplete Membership Oracle",
journal = "Machine Learning",
volume = "14",
number = "1",
pages = "7-26",
year = "1994",
url = "citeseer.ist.psu.edu/angluin94randomly.html" }
Citations (may not include all citations):537 A theory of the learnable (context) - Valiant - 1984
441 Queries and concept learning (context) - Angluin - 1988
244 Learning regular sets from queries and counterexamples (context) - Angluin - 1987
184 Cryptographic limitations on learning boolean formulae and f.. - Kearns, Valiant - 1989
142 Learning from noisy examples (context) - Angluin, Laird - 1988
97 Learning read-once formulas with queries - Angluin, Hellerstein et al. - 1993
84 Learning disjunctions of conjunctions (context) - Valiant - 1985
84 Learning conjunctions of Horn clauses - Angluin, Frazier et al. - 1992
82 When won't membership queries help (context) - Angluin, Kharitonov - 1991
78 the learnability of Boolean formulae - Kearns, Li et al. - 1987
67 Negative results for equivalence queries (context) - Angluin - 1990
40 Types of noise in data for concept learning (context) - Sloan - 1988
40 Probabilistic recurrence relations (context) - Karp - 1991
28 DNF with noise in the attributes (context) - Shackelford, Volper - 1988
21 Exact identification of circuits using fixed points of ampli.. (context) - Goldman, Kearns et al. - 1990
19 On learning from queries and counterexamples in the presence.. (context) - Sakakibara - 1991
13 line learning with an oblivious environment and the power of.. (context) - Maass - 1991
9 Polynomial time learnability of simple deterministic languag.. (context) - Ishizaka - 1990
8 Identifying -formula decision trees with queries (context) - Hancock - 1990
7 Learning monotone DNF with an incomplete membership oracle - Angluin, Slonim - 1991
6 Learning switch configurations (context) - Raghavan, Schach - 1990
3 Computational Learning Theory: New Models and Algorithms (context) - Sloan - 1989
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.toc.lcs.mit.edu/~slonim/incomplete.html):
Learning Monotone DNF with an Incomplete Membership Oracle - Dana Angluin (1991) (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