Sciweavers

658 search results - page 46 / 132
» Open problems in the security of learning
Sort
View
AAAI
2006
13 years 10 months ago
Predicting Electricity Distribution Feeder Failures Using Machine Learning Susceptibility Analysis
A Machine Learning (ML) System known as ROAMS (Ranker for Open-Auto Maintenance Scheduling) was developed to create failure-susceptibility rankings for almost one thousand 13.8kV-...
Philip Gross, Albert Boulanger, Marta Arias, David...
PERCOM
2010
ACM
13 years 7 months ago
ReSCo: A middleware component for Reliable Service Composition in pervasive systems
Abstract—Service composition schemes create high-level application services by combining several basic services. Service composition schemes for dynamic, open systems, such as th...
Brent Lagesse, Mohan Kumar, Matthew Wright
TAMC
2007
Springer
14 years 3 months ago
A Note on Universal Composable Zero Knowledge in Common Reference String Model
Pass observed that universal composable zero-knowledge (UCZK) protocols in the common reference string (CRS) model, where a common reference string is selected trustily by a truste...
Andrew Chi-Chih Yao, Frances F. Yao, Yunlei Zhao
CEC
2008
IEEE
13 years 11 months ago
Subtree deactivation control with grammatical Genetic Programming in dynamic environments
Abstract-- We investigate the usefulness of a subtree deactivation control mechanism which is open to evolutionary learning. It is hypothesised that this representation confers an ...
Michael O'Neill, Anthony Brabazon, Erik Hemberg
NECO
2008
146views more  NECO 2008»
13 years 9 months ago
Deep, Narrow Sigmoid Belief Networks Are Universal Approximators
In this paper we show that exponentially deep belief networks [3, 7, 4] can approximate any distribution over binary vectors to arbitrary accuracy, even when the width of each lay...
Ilya Sutskever, Geoffrey E. Hinton