(Enter summary)
Abstract: Two extensions of the Linial, Mansour, Nisan AC 0 learning algorithm are presented. The LMN method works when input examples are drawn uniformly. The new algorithms improve on theirs by performing well when given inputs drawn from unknown, mutually independent distributions. A variant of the one of the algorithms is conjectured to work in an even broader setting. 1 INTRODUCTION Linial, Mansour, and Nisan [LMN89] introduced the use of the Fourier transform to accomplish Boolean function... (Update)
Context of citations to this paper: More
.... [f(x) 6= f(x Phi e i ) I D;i (f) The Fourier transform of Boolean functions over product distribution is defined as follows (see [FJS91]) First we define the inner product over the 2 dimensional vector space of all real valued functions over f0; 1g as follows: f; g) D...
Cited by: More
A Resampling Technique for Learning the Fourier Spectrum of - Skewed Data Rajeev
(Correct)
Weakly Learning DNF and Characterizing Statistical - Query Learning Using
(Correct)
Efficient Noise-Tolerant Learning From Statistical Queries - Kearns (1998)
(Correct)
Active bibliography (related documents): More All
0.3: The Fourier Transform in Computational Learning Theory - Sun (1996)
(Correct)
0.3: An Efficient Membership-Query Algorithm for Learning DNF with.. - Jackson (1994)
(Correct)
0.1: Galois Field Circuits and Realization of Multiple-Valued Logic .. - Zeljko Zilic (1993)
(Correct)
Similar documents based on text: More All
0.3: A slight sharpening of LMN - Håstad (2002)
(Correct)
0.2: The Expressive Power of Voting Polynomials - Aspnes, Beigel, Furst, Rudich (1993)
(Correct)
0.2: On the Fourier Spectrum of Monotone Functions - Bshouty, Tamon (1996)
(Correct)
Related documents from co-citation: More All
10: The Computational Complexity of Machine Learning (context) - Kearns - 1990
10: the learnability of boolean formulae
- Kearns, Li et al. - 1987
10: Constant depth circuits (context) - Linial, Mansour et al. - 1993
BibTeX entry: (Update)
M. L. Furst, J. C. Jackson, and S. W. Smith. Improved learning of AC 0 functions. In Proc. 4th Annu. Workshop on Comput. Learning Theory, pages 317--325. Morgan Kaufmann, San Mateo, CA, 1991. http://citeseer.ist.psu.edu/furst91improved.html More
@inproceedings{ furst91improved,
author = "Merrick L. Furst and Jeffrey C. Jackson and Sean W. Smith",
title = "Improved Learning of {AC} 0 Functions",
booktitle = "Computational Learing Theory",
pages = "317-325",
year = "1991",
url = "citeseer.ist.psu.edu/furst91improved.html" }
Citations (may not include all citations):
1749
An Introduction to Probability Theory and Its Applications (context) - Feller - 1957
493
Communications of the ACM (context) - Valiant, of et al. - 1984
375
Probability inequalities for sums of bounded random variable.. (context) - Hoeffding - 1963
163
NP is as easy as detecting unique solutions (context) - Valiant, Vazirani - 1985 ACM DBLP
141
The complexity of finite functions (context) - Boppana, Sipser - 1990 ACM DBLP
75
and the polynomial time hierarchy (context) - Furst, Saxe et al. - 1981
68
Computational Limitations for Small Depth Circuits (context) - Hastad - 1986
66
Constant depth circuits (context) - Linial, Mansour et al. - 1989
60
Generic oracles and oracle classes (context) - Blum, Impagliazzo - 1987
12
and the polynomial hierarchy (context) - Tarui, threshold - 1991
10
A representation of the joint distribution of responses to n.. (context) - Bahadur - 1961
6
Personal communication (context) - Vazirani
6
Technical Report YALEU/DCS/TR (context) - Beigel, Reingold et al. - 1990
3
The spectral norm of finite functions
- Bellare - 1991 ACM
1
Personal communication (context) - Smolensky
The graph only includes citing articles where the year of publication is known.
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