Authors: Todorovic, Branimir
Stanković, Miomir 
Moraga, Claudio
Title: Gaussian sum filters for recurrent neural networks training
Journal: 8th Seminar on Neural Network Applications in Electrical Engineering, Neurel-2006 Proceedings
First page: 53
Last page: 57
Issue Date: 1-Dec-2006
ISBN: 1-4244-0433-9
DOI: 10.1109/NEUREL.2006.341175
Abstract: 
We consider the problem of recurrent neural network training as a Bayesian state estimation. The proposed algorithm uses Gaussian sum filter for nonlinear, non-Gaussian estimation of network outputs and synaptic weights. The performances of the proposed algorithm and other Bayesian filters are compared in noisy chaotic time series long-term prediction.
Keywords: Divided difference filter | Extended Kalman filter | Gaussian sum filter | Recurrent neural networks | Sequential Bayesian estimation | Unscented kalman filter
Publisher: IEEE

Show full item record

SCOPUSTM   
Citations

1
checked on Jun 21, 2024

Page view(s)

38
checked on May 9, 2024

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.