Sciweavers

1601 search results - page 106 / 321
» Learning Gaussian processes from multiple tasks
Sort
View
131
Voted
DAC
1996
ACM
15 years 7 months ago
Constructing Application-Specific Heterogeneous Embedded Architectures from Custom HW/SW Applications
Deep sub-micron processing technologies have enabled the implementation of new application-specificembeddedarchitecturesthat integrate multiple software programmable processors (e...
Steven Vercauteren, Bill Lin, Hugo De Man
150
Voted
ICASSP
2011
IEEE
14 years 7 months ago
Use of VTL-wise models in feature-mapping framework to achieve performance of multiple-background models in speaker verification
Recently, Multiple Background Models (M-BMs) [1, 2] have been shown to be useful in speaker verification, where the M-BMs are formed based on different Vocal Tract Lengths (VTLs)...
Achintya Kumar Sarkar, Srinivasan Umesh
138
Voted
ICML
2010
IEEE
15 years 4 months ago
Learning Temporal Causal Graphs for Relational Time-Series Analysis
Learning temporal causal graph structures from multivariate time-series data reveals important dependency relationships between current observations and histories, and provides a ...
Yan Liu 0002, Alexandru Niculescu-Mizil, Aurelie C...
116
Voted
VLDB
2002
ACM
126views Database» more  VLDB 2002»
15 years 3 months ago
ALIAS: An Active Learning led Interactive Deduplication System
Deduplication, a key operation in integrating data from multiple sources, is a time-consuming, labor-intensive and domainspecific operation. We present our design of alias that us...
Sunita Sarawagi, Anuradha Bhamidipaty, Alok Kirpal...
JMLR
2002
133views more  JMLR 2002»
15 years 3 months ago
Learning Precise Timing with LSTM Recurrent Networks
The temporal distance between events conveys information essential for numerous sequential tasks such as motor control and rhythm detection. While Hidden Markov Models tend to ign...
Felix A. Gers, Nicol N. Schraudolph, Jürgen S...