Sciweavers

1627 search results - page 236 / 326
» Multi-Instance Mixture Models
Sort
View
107
Voted
ICCSA
2003
Springer
15 years 7 months ago
Robust Speaker Recognition Against Utterance Variations
A speaker model in speaker recognition system is to be trained from a large data set gathered in multiple sessions. Large data set requires large amount of memory and computation, ...
JongJoo Lee, JaeYeol Rheem, Ki Yong Lee
ISSTA
1998
ACM
15 years 6 months ago
Verifying Systems with Integer Constraints and Boolean Predicates: A Composite Approach
Symbolic model checking has proved highly successful for large nite-state systems, in which states can be compactly encoded using binary decision diagrams (BDDs) or their variants...
Tevfik Bultan, Richard Gerber, Christopher League
139
Voted
AIRS
2006
Springer
15 years 6 months ago
Learning to Separate Text Content and Style for Classification
Many text documents naturally have two kinds of labels. For example, we may label web pages from universities according to their categories, such as "student" or "fa...
Dell Zhang, Wee Sun Lee
140
Voted
NECO
1998
168views more  NECO 1998»
15 years 2 months ago
Constructive Incremental Learning from Only Local Information
We introduce a constructive, incremental learning system for regression problems that models data by means of spatially localized linear models. In contrast to other approaches, t...
Stefan Schaal, Christopher G. Atkeson
152
Voted
NN
2010
Springer
225views Neural Networks» more  NN 2010»
15 years 29 days ago
Learning to imitate stochastic time series in a compositional way by chaos
This study shows that a mixture of RNN experts model can acquire the ability to generate sequences that are combination of multiple primitive patterns by means of self-organizing ...
Jun Namikawa, Jun Tani