Sciweavers

37 search results - page 6 / 8
» On the Concentration of Expectation and Approximate Inferenc...
Sort
View
ENGL
2006
108views more  ENGL 2006»
13 years 7 months ago
A Fuzzy-Neuro Model for Normal Concrete Mix Design
: Concrete mix design is a process of proportioning the ingredients in right proportions. Though it is based on sound technical principles and heuristics, the entire process is not...
M. C. Nataraja, M. A. Jayaram, C. N. Ravikumar
ICANN
2009
Springer
14 years 2 days ago
An EM Based Training Algorithm for Recurrent Neural Networks
Recurrent neural networks serve as black-box models for nonlinear dynamical systems identification and time series prediction. Training of recurrent networks typically minimizes t...
Jan Unkelbach, Yi Sun, Jürgen Schmidhuber
MOBIHOC
2008
ACM
14 years 7 months ago
Dynamic packet fragmentation for wireless channels with failures
It was shown recently [7?9], under quite general conditions, that retransmission-based protocols may result in power-law delays and possibly zero throughput even if the distributi...
Predrag R. Jelenkovic, Jian Tan
NECO
2011
13 years 2 months ago
Collective Stability of Networks of Winner-Take-All Circuits
The neocortex has a remarkably uniform neuronal organization, suggesting that common principles of processing are employed throughout its extent. In particular, the patterns of co...
Ueli Rutishauser, Rodney J. Douglas, Jean-Jacques ...
NN
2000
Springer
192views Neural Networks» more  NN 2000»
13 years 7 months ago
A new algorithm for learning in piecewise-linear neural networks
Piecewise-linear (PWL) neural networks are widely known for their amenability to digital implementation. This paper presents a new algorithm for learning in PWL networks consistin...
Emad Gad, Amir F. Atiya, Samir I. Shaheen, Ayman E...