Sciweavers

772 search results - page 138 / 155
» Hyper-Systolic Matrix Multiplication
Sort
View
KDD
2012
ACM
207views Data Mining» more  KDD 2012»
11 years 11 months ago
Robust multi-task feature learning
Multi-task learning (MTL) aims to improve the performance of multiple related tasks by exploiting the intrinsic relationships among them. Recently, multi-task feature learning alg...
Pinghua Gong, Jieping Ye, Changshui Zhang
BMCBI
2011
13 years 3 months ago
PheMaDB: A solution for storage, retrieval, and analysis of high throughput phenotype data
Background: OmniLog™ phenotype microarrays (PMs) have the capability to measure and compare the growth responses of biological samples upon exposure to hundreds of growth condit...
Wenling E. Chang, Keri Sarver, Brandon W. Higgs, T...
CVPR
1997
IEEE
14 years 25 days ago
Multi-Modal Tracking of Faces for Video Communications
This paper describes a system which uses multiple visual processes to detect and track faces for video compression and transmission. The system is based on an architecture in whic...
James L. Crowley, François Bérard
BIBE
2007
IEEE
159views Bioinformatics» more  BIBE 2007»
14 years 19 days ago
Non-negative Tensor Factorization Based on Alternating Large-scale Non-negativity-constrained Least Squares
Non-negative matrix factorization (NMF) and non-negative tensor factorization (NTF) have attracted much attention and have been successfully applied to numerous data analysis probl...
Hyunsoo Kim, Haesun Park, Lars Eldén
SAIG
2000
Springer
14 years 6 days ago
Code Generators for Automatic Tuning of Numerical Kernels: Experiences with FFTW
Achieving peak performance in important numerical kernels such as dense matrix multiply or sparse-matrix vector multiplication usually requires extensive, machine-dependent tuning ...
Rich Vuduc, James Demmel