Sciweavers

256 search results - page 38 / 52
» Optimal transfer function neural networks
Sort
View
TIT
1998
126views more  TIT 1998»
13 years 7 months ago
An Asymptotic Property of Model Selection Criteria
—Probability models are estimated by use of penalized log-likelihood criteria related to AIC and MDL. The accuracies of the density estimators are shown to be related to the trad...
Yuhong Yang, Andrew R. Barron
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...
GECCO
2007
Springer
178views Optimization» more  GECCO 2007»
14 years 2 months ago
Coevolution of intelligent agents using cartesian genetic programming
A coevolutionary competitive learning environment for two antagonistic agents is presented. The agents are controlled by a new kind of computational network based on a compartment...
Gul Muhammad Khan, Julian Francis Miller, David M....
IEEEPACT
2008
IEEE
14 years 2 months ago
Feature selection and policy optimization for distributed instruction placement using reinforcement learning
Communication overheads are one of the fundamental challenges in a multiprocessor system. As the number of processors on a chip increases, communication overheads and the distribu...
Katherine E. Coons, Behnam Robatmili, Matthew E. T...
PRL
1998
132views more  PRL 1998»
13 years 7 months ago
Unsupervised feature selection using a neuro-fuzzy approach
A neuro-fuzzy methodology is described which involves connectionist minimization of a fuzzy feature evaluation index with unsupervised training. The concept of a ¯exible membersh...
Jayanta Basak, Rajat K. De, Sankar K. Pal