Sciweavers

221 search results - page 15 / 45
» Computing arbitrary functions of encrypted data
Sort
View
ATAL
2007
Springer
14 years 1 months ago
Model-based function approximation in reinforcement learning
Reinforcement learning promises a generic method for adapting agents to arbitrary tasks in arbitrary stochastic environments, but applying it to new real-world problems remains di...
Nicholas K. Jong, Peter Stone
IFL
1997
Springer
153views Formal Methods» more  IFL 1997»
13 years 11 months ago
Common Subexpressions Are Uncommon in Lazy Functional Languages
Common subexpression elimination is a well-known compiler optimisation that saves time by avoiding the repetition of the same computation. In lazy functional languages, referential...
Olaf Chitil
CORR
2006
Springer
102views Education» more  CORR 2006»
13 years 7 months ago
Theoretical Properties of Projection Based Multilayer Perceptrons with Functional Inputs
Many real world data are sampled functions. As shown by Functional Data Analysis (FDA) methods, spectra, time series, images, gesture recognition data, etc. can be processed more e...
Fabrice Rossi, Brieuc Conan-Guez
IAW
2003
IEEE
14 years 28 days ago
Assuring Consistency and Increasing Reliability in Group Communication Mechanisms in Computational Resiliency
— The Computational Resiliency library (CRLib) provides distributed systems with the ability to sustain operation and dynamically restore the level of assurance in system functio...
Norka B. Lucena, Steve J. Chapin, Joohan Lee
NIPS
1998
13 years 9 months ago
Coding Time-Varying Signals Using Sparse, Shift-Invariant Representations
A common way to represent a time series is to divide it into shortduration blocks, each of which is then represented by a set of basis functions. A limitation of this approach, ho...
Michael S. Lewicki, Terrence J. Sejnowski