Sciweavers

352 search results - page 32 / 71
» On implementation choices for iterative improvement partitio...
Sort
View
ICML
2009
IEEE
14 years 3 months ago
Using fast weights to improve persistent contrastive divergence
The most commonly used learning algorithm for restricted Boltzmann machines is contrastive divergence which starts a Markov chain at a data point and runs the chain for only a few...
Tijmen Tieleman, Geoffrey E. Hinton
ACSC
2003
IEEE
14 years 24 days ago
Efficient Trie-Based Sorting of Large Sets of Strings
Sorting is a fundamental algorithmic task. Many generalpurpose sorting algorithms have been developed, but efficiency gains can be achieved by designing algorithms for specific ki...
Ranjan Sinha, Justin Zobel
IPPS
1999
IEEE
14 years 1 months ago
Compiler Analysis to Support Compiled Communication for HPF-Like Programs
By managing network resources at compile time, the compiled communication technique greatly improves the communication performance for communication patterns that are known at com...
Xin Yuan, Rajiv Gupta, Rami G. Melhem
TVLSI
1998
124views more  TVLSI 1998»
13 years 8 months ago
Computing support-minimal subfunctions during functional decomposition
Abstract— The growing popularity of look-up table (LUT)based field programmable gate arrays (FPGA’s) has renewed the interest in functional or Roth–Karp decomposition techni...
Christian Legl, Bernd Wurth, Klaus Eckl
ICCV
1995
IEEE
14 years 20 days ago
In Defence of the 8-Point Algorithm
The fundamental matrix is a basic tool in the analysis of scenes taken with two uncalibrated cameras, and the 8-point algorithm is a frequently cited method for computing the fund...
Richard I. Hartley