Sciweavers

329 search results - page 13 / 66
» Probably Approximately Correct Learning
Sort
View
AAAI
1997
13 years 8 months ago
Bayes Networks for Estimating the Number of Solutions to a CSP
The problem of counting the number of solutions to a constraint satisfaction problem (CSP) is rephrased in terms of probability updating in Bayes networks. Approximating the proba...
Amnon Meisels, Solomon Eyal Shimony, Gadi Solotore...
STOC
1993
ACM
141views Algorithms» more  STOC 1993»
13 years 11 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
EMMCVPR
2005
Springer
14 years 1 months ago
Color Correction of Underwater Images for Aquatic Robot Inspection
In this paper, we consider the problem of color restoration using statistical priors. This is applied to color recovery for underwater images, using an energy minimization formulat...
Luz Abril Torres-Méndez, Gregory Dudek
AAAI
1992
13 years 8 months ago
Inferring Finite Automata with Stochastic Output Functions and an Application to Map Learning
It is often useful for a robot to construct a spatial representation of its environment from experiments and observations, in other words, to learn a map of its environment by exp...
Thomas Dean, Dana Angluin, Kenneth Basye, Sean P. ...
STOC
2005
ACM
150views Algorithms» more  STOC 2005»
14 years 7 months ago
Correcting errors without leaking partial information
This paper explores what kinds of information two parties must communicate in order to correct errors which occur in a shared secret string W. Any bits they communicate must leak ...
Yevgeniy Dodis, Adam Smith