Sciweavers

31 search results - page 6 / 7
» Efficient Digital Pre-filtering for Least-Squares Linear App...
Sort
View
KDD
2009
ACM
188views Data Mining» more  KDD 2009»
14 years 6 months ago
Mining discrete patterns via binary matrix factorization
Mining discrete patterns in binary data is important for subsampling, compression, and clustering. We consider rankone binary matrix approximations that identify the dominant patt...
Bao-Hong Shen, Shuiwang Ji, Jieping Ye
NN
2000
Springer
192views Neural Networks» more  NN 2000»
13 years 5 months ago
A new algorithm for learning in piecewise-linear neural networks
Piecewise-linear (PWL) neural networks are widely known for their amenability to digital implementation. This paper presents a new algorithm for learning in PWL networks consistin...
Emad Gad, Amir F. Atiya, Samir I. Shaheen, Ayman E...
CVPR
2009
IEEE
1372views Computer Vision» more  CVPR 2009»
15 years 26 days ago
Blind motion deblurring from a single image using sparse approximation
Restoring a clear image from a single motion-blurred image due to camera shake has long been a challenging problem in digital imaging. Existing blind deblurring techniques eithe...
Jian-Feng Cai (National University of Singapore), ...
ASAP
2004
IEEE
140views Hardware» more  ASAP 2004»
13 years 9 months ago
Decimal Floating-Point Division Using Newton-Raphson Iteration
Decreasing feature sizes allow additional functionality to be added to future microprocessors to improve the performance of important application domains. As a result of rapid gro...
Liang-Kai Wang, Michael J. Schulte
SIGMOD
2009
ACM
235views Database» more  SIGMOD 2009»
14 years 6 months ago
Quality and efficiency in high dimensional nearest neighbor search
Nearest neighbor (NN) search in high dimensional space is an important problem in many applications. Ideally, a practical solution (i) should be implementable in a relational data...
Yufei Tao, Ke Yi, Cheng Sheng, Panos Kalnis