Sciweavers

1316 search results - page 97 / 264
» Comparing mathematical models on the problem of network infe...
Sort
View
DSOM
2007
Springer
16 years 9 days ago
Probabilistic Fault Diagnosis Using Adaptive Probing
Past research on probing-based network monitoring provides solutions based on preplanned probing which is computationally expensive, is less accurate, and involves a large manageme...
Maitreya Natu, Adarshpal S. Sethi
PPSN
2004
Springer
15 years 11 months ago
Coupling of Evolution and Learning to Optimize a Hierarchical Object Recognition Model
Abstract. A key problem in designing artificial neural networks for visual object recognition tasks is the proper choice of the network architecture. Evolutionary optimization met...
Georg Schneider, Heiko Wersing, Bernhard Sendhoff,...
IBPRIA
2003
Springer
15 years 11 months ago
A Probabilistic Model for the Cooperative Modular Neural Network
Abstract. This paper presents a model for the probability of correct classification for the Cooperative Modular Neural Network (CMNN). The model enables the estimation of the perf...
Luís A. Alexandre, Aurélio C. Campil...
BMCBI
2006
118views more  BMCBI 2006»
15 years 6 months ago
Predicting the effect of missense mutations on protein function: analysis with Bayesian networks
Background: A number of methods that use both protein structural and evolutionary information are available to predict the functional consequences of missense mutations. However, ...
Chris J. Needham, James R. Bradford, Andrew J. Bul...
ICANN
2009
Springer
15 years 10 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