Sciweavers

101 search results - page 14 / 21
» Automatic generation of a neural network architecture using ...
Sort
View
NECO
2007
115views more  NECO 2007»
13 years 7 months ago
Training Recurrent Networks by Evolino
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Jürgen Schmidhuber, Daan Wierstra, Matteo Gag...
CGO
2010
IEEE
14 years 2 months ago
Automatic creation of tile size selection models
Tiling is a widely used loop transformation for exposing/exploiting parallelism and data locality. Effective use of tiling requires selection and tuning of the tile sizes. This is...
Tomofumi Yuki, Lakshminarayanan Renganarayanan, Sa...
NIPS
1997
13 years 8 months ago
Computing with Action Potentials
Most computational engineering based loosely on biology uses continuous variables to represent neural activity. Yet most neurons communicate with action potentials. The engineerin...
John J. Hopfield, Carlos D. Brody, Sam T. Roweis
DAC
2008
ACM
14 years 8 months ago
Concurrent topology and routing optimization in automotive network integration
In this paper, a novel automatic approach for the concurrent topology and routing optimization that achieves a high quality network layout is proposed. This optimization is based ...
Bardo Lang, Christian Haubelt, Jürgen Teich, ...
ISMB
2000
13 years 8 months ago
Prediction of the Number of Residue Contacts in Proteins
Knowing the number of residue contacts in a protein is crucial for deriving constraints useful in modeling protein folding, protein structure, and/or scoring remote homology searc...
Piero Fariselli, Rita Casadio