Sciweavers

1936 search results - page 8 / 388
» Unbundling Active Functionality
Sort
View
ICML
1998
IEEE
14 years 8 months ago
Q2: Memory-Based Active Learning for Optimizing Noisy Continuous Functions
This paper introduces a new algorithm, Q2, foroptimizingthe expected output ofamultiinput noisy continuous function. Q2 is designed to need only a few experiments, it avoids stron...
Andrew W. Moore, Jeff G. Schneider, Justin A. Boya...
NN
2008
Springer
13 years 7 months ago
Two k-winners-take-all networks with discontinuous activation functions
This paper presents two k-winners-take-all (k-WTA) networks with discontinuous activation functions. The k-WTA operation is first converted equivalently into linear and quadratic ...
Qingshan Liu, Jun Wang
FGR
2006
IEEE
157views Biometrics» more  FGR 2006»
14 years 1 months ago
Evaluating Error Functions for Robust Active Appearance Models
Active appearance models (AAMs) are generative parametric models commonly used to track faces in video sequences. A limitation of AAMs is they are not robust to occlusion. A recen...
Barry-John Theobald, Iain Matthews, Simon Baker
ISBI
2008
IEEE
14 years 8 months ago
Real-time segmentation of 4D ultrasound by Active Geometric Functions
Four-dimensional ultrasound based on matrix phased array transducers can capture the complex 4D cardiac motion in a complete and real-time fashion. However, the large amount of in...
Qi Duan, Elsa D. Angelini, Shunichi Homma, Andrew ...