Sciweavers

4072 search results - page 388 / 815
» Designing an Optimal Network Using the Cross-Entropy Method
Sort
View
170
Voted
ASC
2006
15 years 4 months ago
Speeding up the learning of equivalence classes of bayesian network structures
For some time, learning Bayesian networks has been both feasible and useful in many problems domains. Recently research has been done on learning equivalence classes of Bayesian n...
Rónán Daly, Qiang Shen, J. Stuart Ai...
ECML
2007
Springer
15 years 11 months ago
Nondeterministic Discretization of Weights Improves Accuracy of Neural Networks
Abstract. The paper investigates modification of backpropagation algorithm, consisting of discretization of neural network weights after each training cycle. This modification, a...
Marcin Wojnarski
DATE
2003
IEEE
154views Hardware» more  DATE 2003»
15 years 10 months ago
Packetized On-Chip Interconnect Communication Analysis for MPSoC
Interconnect networks play a critical role in shared memory multiprocessor systems-on-chip (MPSoC) designs. MPSoC performance and power consumption are greatly affected by the pac...
Terry Tao Ye, Luca Benini, Giovanni De Micheli
ISLPED
2007
ACM
109views Hardware» more  ISLPED 2007»
15 years 6 months ago
A multi-model power estimation engine for accuracy optimization
RTL power macromodeling is a mature research topic with a variety of equation and table-based approaches. Despite its maturity, macromodeling is not yet widely accepted as an indu...
Felipe Klein, Guido Araujo, Rodolfo Azevedo, Rober...
ICPADS
2002
IEEE
15 years 9 months ago
Experiences in Building a Scalable Distributed Network Emulation System
Network emulation systems are widely used to explore the behavior of network protocols and to test and evaluate protocol implementations and applications. The major problem of net...
Pei Zheng, Lionel M. Ni