Sciweavers

3635 search results - page 362 / 727
» Algorithms for Energy Saving
Sort
View
ESANN
2008
15 years 8 months ago
A Regularized Learning Method for Neural Networks Based on Sensitivity Analysis
The Sensitivity-Based Linear Learning Method (SBLLM) is a learning method for two-layer feedforward neural networks, based on sensitivity analysis, that calculates the weights by s...
Bertha Guijarro-Berdiñas, Oscar Fontenla-Ro...
174
Voted
DM
2010
90views more  DM 2010»
15 years 6 months ago
The firefighter problem for cubic graphs
We show that the firefighter problem is NP-complete for cubic graphs. We also show that given a rooted tree of maximum degree three in which every leaf is the same distance from t...
Andrew King, Gary MacGillivray
TVLSI
2002
107views more  TVLSI 2002»
15 years 6 months ago
Low-power clock distribution using multiple voltages and reduced swings
: Clock networks account for a significant fraction of the power dissipation of a chip and are critical to performance. This paper presents theory and algorithms for building a low...
Jatuchai Pangjun, Sachin S. Sapatnekar
ICML
2008
IEEE
16 years 7 months ago
Empirical Bernstein stopping
Sampling is a popular way of scaling up machine learning algorithms to large datasets. The question often is how many samples are needed. Adaptive stopping algorithms monitor the ...
Csaba Szepesvári, Jean-Yves Audibert, Volod...
GLOBECOM
2008
IEEE
16 years 1 months ago
Reduced Complexity ML Detection for Differential Unitary Space-Time Modulation with Carrier Frequency Offset
— Recently, a maximum likelihood (ML) detection rule for differential unitary space time modulation (DUSTM) under the existence of unknown carrier frequency offset (CFO) has been...
Feifei Gao, Arumugam Nallanathan, Chintha Tellambu...