Sciweavers

STOC
1993
ACM
179views Algorithms» more  STOC 1993»
14 years 3 months ago
The network inhibition problem
We study the Maximum Flow Network Interdiction Problem (MFNIP). We present two classes of polynomially separable valid inequalities for Cardinality MFNIP. We also prove the integr...
Cynthia A. Phillips
STOC
1993
ACM
85views Algorithms» more  STOC 1993»
14 years 3 months ago
What can be computed locally?
Moni Naor, Larry J. Stockmeyer
STOC
1993
ACM
94views Algorithms» more  STOC 1993»
14 years 3 months ago
Finiteness results for sigmoidal "neural" networks
Angus Macintyre, Eduardo D. Sontag
STOC
1993
ACM
141views Algorithms» more  STOC 1993»
14 years 3 months ago
Bounds for the computational power and learning complexity of analog neural nets
Abstract. It is shown that high-order feedforward neural nets of constant depth with piecewisepolynomial activation functions and arbitrary real weights can be simulated for Boolea...
Wolfgang Maass
STOC
1993
ACM
123views Algorithms» more  STOC 1993»
14 years 3 months ago
Constructing small sample spaces satisfying given constraints
Abstract. The subject of this paper is nding small sample spaces for joint distributions of n discrete random variables. Such distributions are often only required to obey a certa...
Daphne Koller, Nimrod Megiddo
STOC
1993
ACM
117views Algorithms» more  STOC 1993»
14 years 3 months ago
Efficient noise-tolerant learning from statistical queries
In this paper, we study the problem of learning in the presence of classification noise in the probabilistic learning model of Valiant and its variants. In order to identify the cl...
Michael J. Kearns
STOC
1993
ACM
120views Algorithms» more  STOC 1993»
14 years 3 months ago
Characterizing non-deterministic circuit size
Mauricio Karchmer, Avi Wigderson