Abstract:
Abstract. We construct a predicate that is computable by a perceptron with linear size, order 1, and exponential weights, but which cannot be computed by any perceptron having subexponential (2 n o(1)) size, subpolynomial
Citations
|
174
|
Introduction to Approximation Theory
– Cheney
- 1966
|
|
164
|
PP is as hard as the polynomial-time hierarchy
– Toda
- 1991
|
|
108
|
Approximation of Functions
– Lorentz
- 1966
|
|
87
|
Pp is closed under intersection
– Beigel, Reingold, et al.
- 1995
|
|
82
|
A note on the power of threshold circuits
– Allender
- 1989
|
|
69
|
Counting classes are at least as hard as the polynomial-time hierarchy
– Toda, Ogiwara
- 1992
|
|
68
|
The Expressive Power of Voting Polynomials
– Aspnes, Beigel, et al.
- 1994
|
|
44
|
On truth-table reducibility to SAT
– Buss, Hay
- 1991
|
|
30
|
A survey on counting classes
– Gundermann, Nasser, et al.
- 1990
|
|
25
|
The perceptron strikes back
– Beigel, Reingold, et al.
- 1991
|
|
21
|
the Polynomial-Time Hierarchy
– Parity
- 1984
|
|
18
|
Probabilistic polynomial time is closed under parity reductions
– Beigel, Hemachandra, et al.
- 1991
|
|
13
|
A comparison of Uniform Approximations on an interval and a finite subset thereof
– Rivlin, Cheney
- 1966
|
|
9
|
Separating PH from PP by relativization
– Fu
- 1992
|
|
5
|
On the power of probabilistic polynomial time: P NP[log] ` PP
– Hemachandra, Wechsung
- 1989
|
|
2
|
olya and G. Szeg o, Problems and Theorems in Analysis I
– P'
- 1972
|
|
1
|
Expanded version of the original 1968 edition
– Minsky, Papert, et al.
- 1988
|
|
