Using techniques from learning theory, we show that any s-term DNF over n variables can be computed by a perceptron of order O((n log n) 1=3 log s). This upper bound matches, up to a polylogarithmic factor, the longstanding lower bound given by Minsky and Papert in their 1968 book Perceptrons. As a consequence of this upper bound we obtain the fastest known algorithm
|
1364
|
A theory of the learnable
– Valiant
- 1984
|
|
536
|
Learnability and the Vapnik-Chervonenkis Dimension
– Blumer, Ehrenfeucht, et al.
- 1989
|
|
528
|
Queries and concept learning
– Angluin
- 1988
|
|
511
|
Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm
– Littlestone
- 1988
|
|
298
|
Boosting a weak learning algorithm by majority
– Freund
- 1995
|
|
189
|
Large margin classification using the perceptron algorithm
– Freund, Schapire
- 1999
|
|
175
|
A general lower bound on the number of examples needed for learning
– Ehrenfeucht, Haussler, et al.
- 1989
|
|
174
|
Introduction to Approximation Theory
– Cheney
- 1966
|
|
116
|
An efficient membership-query algorithm for learning DNF with respect to the uniform distribution
– Jackson
- 1997
|
|
80
|
Weakly learning DNF and characterizing statistical query learning using Fourier analysis
– Blum, Furst, et al.
- 1994
|
|
68
|
The Expressive Power of Voting Polynomials
– Aspnes, Beigel, et al.
- 1994
|
|
66
|
Majority gates vs. general weighted threshold gates
– Goldmann, HËšastad, et al.
- 1992
|
|
54
|
Learning decision trees from random examples
– Ehrenfeucht, Haussler
- 1989
|
|
49
|
The perceptron algorithm vs. Winnow: linear vs. logarithmic mistake bounds when few input variables are relevant
– Kivinen, Warmuth, et al.
- 1997
|
|
47
|
The polynomial method in circuit complexity
– Beigel
- 1993
|
|
47
|
Fast learning of k-term DNF formulas with queries
– Blum, Rudich
- 1995
|
|
34
|
Learning DNF under the uniform distribution in quasi-polynomial time
– Verbeurgt
- 1990
|
|
33
|
Learning nested differences of intersection-closed concept classes
– Helmbold, Sloan, et al.
- 1990
|
|
30
|
Learning noisy perceptrons by a perceptron in polynomial time
– Cohen
- 1997
|
|
26
|
On using the Fourier transform to learn disjoint
– Khardon
|
|
26
|
On learning visual concepts and DNF formulae
– Kushilevitz, Roth
- 1993
|
|
25
|
The perceptron strikes back
– Beigel, Reingold, et al.
- 1991
|
|
21
|
Rank-r decision trees are a subclass of r-decision lists
– Blum
- 1992
|
|
18
|
A polynomial time algorithm for learning noisy linear threshold functions
– Blum, Frieze, et al.
- 1996
|
|
17
|
Learning monotone k DNF formulas on product distributions
– HANCOCK, T, et al.
- 1991
|
|
17
|
On PAC learning using Winnow, Perceptron, and a Perceptron-like algorithm
– Servedio
- 1999
|
|
15
|
Learning sub-classes of monotone DNF on the uniform distribution
– Verbeurgt
- 1998
|
|
14
|
A subexponential exact learning algorithm for DNF using equivalence queries
– Bshouty
- 1996
|
|
14
|
Learning monotone log-term DNF formulas under the uniform distribution. Theory of Computing Systems
– Sakai, Maruoka
- 2000
|
|
13
|
On learning monotone DNF formulae under uniform distributions
– Kucera, Marchetti-Spaccamela, et al.
- 1994
|
|
13
|
Learning DNF by approximating inclusion-exclusion formulae
– Tarui, Tsukiji
- 1999
|
|
9
|
Separating PH from PP by relativization
– Fu
- 1992
|
|
8
|
Identification criteria and lower bounds for Perceptron-like learning rules, Neural Computation 10
– Schmitt
- 1998
|
|
6
|
Worst-case analysis of the perceptron and exponentiated update algorithms
– Bylander
- 1998
|
|
6
|
Approximate inclusion-exclusion. Combinatorica 10:4
– Linial, Nisan
- 1990
|
|
4
|
personal communication
– Beigel
- 2000
|
|
3
|
How fast can a threshold gate learn? in "Computational Learning Theory and Natural Learning Systems: Volume I: Constraints and Prospects
– Maass, Turan
- 1994
|
|
