Sciweavers

52 search results - page 10 / 11
» Performance of universal codes over infinite alphabets
Sort
View
90
Voted
ITSL
2008
15 years 1 months ago
An Empirical Comparison of NML Clustering Algorithms
Clustering can be defined as a data assignment problem where the goal is to partition the data into nonhierarchical groups of items. In our previous work, we suggested an informati...
Petri Kontkanen, Petri Myllymäki
100
Voted
IJCNN
2008
IEEE
15 years 6 months ago
Biologically realizable reward-modulated hebbian training for spiking neural networks
— Spiking neural networks have been shown capable of simulating sigmoidal artificial neural networks providing promising evidence that they too are universal function approximat...
Silvia Ferrari, Bhavesh Mehta, Gianluca Di Muro, A...
83
Voted
ICBA
2004
Springer
197views Biometrics» more  ICBA 2004»
15 years 5 months ago
Maximum Likelihood and Maximum a Posteriori Adaptation for Distributed Speaker Recognition Systems
We apply the ETSI’s DSR standard to speaker verification over telephone networks and investigate the effect of extracting spectral features from different stages of the ETSI...
Chin-Hung Sit, Man-Wai Mak, Sun-Yuan Kung
74
Voted
LCTRTS
2004
Springer
15 years 5 months ago
Finding effective compilation sequences
Most modern compilers operate by applying a fixed, program-independent sequence of optimizations to all programs. Compiler writers choose a single “compilation sequence”, or ...
L. Almagor, Keith D. Cooper, Alexander Grosul, Tim...
100
Voted
ICS
2009
Tsinghua U.
15 years 6 months ago
MPI-aware compiler optimizations for improving communication-computation overlap
Several existing compiler transformations can help improve communication-computation overlap in MPI applications. However, traditional compilers treat calls to the MPI library as ...
Anthony Danalis, Lori L. Pollock, D. Martin Swany,...