Sciweavers

266 search results - page 11 / 54
» Can Saturation Be Parallelised
Sort
View
JMLR
2010
151views more  JMLR 2010»
13 years 2 months ago
Understanding the difficulty of training deep feedforward neural networks
Whereas before 2006 it appears that deep multilayer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with e...
Xavier Glorot, Yoshua Bengio
FCCM
2008
IEEE
212views VLSI» more  FCCM 2008»
14 years 1 months ago
Map-reduce as a Programming Model for Custom Computing Machines
The map-reduce model requires users to express their problem in terms of a map function that processes single records in a stream, and a reduce function that merges all mapped out...
Jackson H. C. Yeung, C. C. Tsang, Kuen Hung Tsoi, ...
CG
2008
Springer
13 years 7 months ago
Parallel techniques for physically based simulation on multi-core processor architectures
As multi-core processor systems become more and more widespread, the demand for efficient parallel algorithms also propagates into the field of computer graphics. This is especial...
Bernhard Thomaszewski, Simon Pabst, Wolfgang Bloch...
EUROPAR
2007
Springer
14 years 1 months ago
Delayed Side-Effects Ease Multi-core Programming
Computer systems are increasingly parallel and heterogeneous, while programs are still largely written in sequential languages. The obvious suggestion that the compiler should auto...
Anton Lokhmotov, Alan Mycroft, Andrew Richards
ICC
1997
IEEE
13 years 11 months ago
Removing Instability and Maximizing Throughput in a Multicast Shuffle-Exchange Network
Multicast capability can be incorporated into any interconnection networks by using a general packet replication scheme previously proposed in [4]. The network can then be used fo...
Cathy W. Chan, Soung C. Liew