Sciweavers

120 search results - page 7 / 24
» Nonmonotonic Inferences in Neural Networks
Sort
View
IWCMC
2010
ACM
13 years 9 months ago
On the use of random neural networks for traffic matrix estimation in large-scale IP networks
Despite a large body of literature and methods devoted to the Traffic Matrix (TM) estimation problem, the inference of traffic flows volume from aggregated data still represents a ...
Pedro Casas, Sandrine Vaton
OL
2011
332views Neural Networks» more  OL 2011»
13 years 2 months ago
A robust implementation of a sequential quadratic programming algorithm with successive error restoration
We consider sequential quadratic programming (SQP) methods for solving constrained nonlinear programming problems. It is generally believed that SQP methods are sensitive to the a...
Klaus Schittkowski
HYBRID
1998
Springer
13 years 11 months ago
A Novel Modular Neural Architecture for Rule-Based and Similarity-Based Reasoning
Hybridconnectionist symbolic systems have been the subject of muchrecent research in AI. By focusing on the implementation of highlevel human cognitive processes e.g., rule-based i...
Rafal Bogacz, Christophe G. Giraud-Carrier
ICIC
2009
Springer
14 years 1 months ago
Solar Radiation Forecasting Using Ad-Hoc Time Series Preprocessing and Neural Networks
In this paper, we present an application of neural networks in the renewable energy domain. We have developed a methodology for the daily prediction of global solar radiation on a ...
Christophe Paoli, Cyril Voyant, Marc Muselli, Mari...
ICANN
2009
Springer
13 years 12 months 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