Sciweavers

2136 search results - page 275 / 428
» Improving on Expectation Propagation
Sort
View
NN
1998
Springer
108views Neural Networks» more  NN 1998»
14 years 9 months ago
How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies
Learning long-term temporal dependencies with recurrent neural networks can be a difficult problem. It has recently been shown that a class of recurrent neural networks called NA...
Tsungnan Lin, Bill G. Horne, C. Lee Giles
95
Voted
TJS
2002
121views more  TJS 2002»
14 years 9 months ago
Precise Data Locality Optimization of Nested Loops
A significant source for enhancing application performance and for reducing power consumption in embedded processor applications is to improve the usage of the memory hierarchy. In...
Vincent Loechner, Benoît Meister, Philippe C...
PAMI
2010
168views more  PAMI 2010»
14 years 8 months ago
Dynamic Hybrid Algorithms for MAP Inference in Discrete MRFs
—In this paper, we present novel techniques that improve the computational and memory efficiency of algorithms for solving multi-label energy functions arising from discrete MRF...
Karteek Alahari, Pushmeet Kohli, Philip H. S. Torr
CORR
2011
Springer
171views Education» more  CORR 2011»
14 years 5 months ago
Design, Implementation and Characterization of a Cooperative Communications System
Cooperative communications is a class of techniques which seek to improve reliability and throughput in wireless systems by pooling the resources of distributed nodes. While coope...
Patrick Murphy, Ashutosh Sabharwal
HPDC
2012
IEEE
13 years 16 days ago
Understanding the effects and implications of compute node related failures in hadoop
Hadoop has become a critical component in today’s cloud environment. Ensuring good performance for Hadoop is paramount for the wide-range of applications built on top of it. In ...
Florin Dinu, T. S. Eugene Ng