Sciweavers

218 search results - page 13 / 44
» Simplifying mixture models through function approximation
Sort
View
ICASSP
2011
IEEE
12 years 11 months ago
Arccosine kernels: Acoustic modeling with infinite neural networks
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
Chih-Chieh Cheng, Brian Kingsbury
ICPR
2010
IEEE
14 years 2 months ago
Integrating a Discrete Motion Model into GMM Based Background Subtraction
GMM based algorithms have become the de facto standard for background subtraction in video sequences, mainly because of their ability to track multiple background distributions, w...
Christian Wolf, Jolion Jolion
SMA
2010
ACM
231views Solid Modeling» more  SMA 2010»
13 years 7 months ago
Conservative swept volume boundary approximation
We present a novel technique for approximating the boundary of a swept volume. The generator given by an input triangle mesh is rendered under all rigid transformations of a discr...
Andreas von Dziegielewski, R. Erbes, Elmar Sch&oum...
EMSOFT
2004
Springer
14 years 1 months ago
Conservative approximations for heterogeneous design
Embedded systems are electronic devices that function in the context of a real environment, by sensing and reacting to a set of stimuli. Because of their close interaction with th...
Roberto Passerone, Jerry R. Burch, Alberto L. Sang...
BIRTHDAY
2008
Springer
13 years 9 months ago
Approximating Behaviors in Embedded System Design
Embedded systems are electronic devices that function in the context of a physical environment, by sensing and reacting to a set of stimuli. To simplify the design of embedded syst...
Roberto Passerone, Alberto L. Sangiovanni-Vincente...