Gaussian sum filters for recurrent neural networks training

DC Field	Value	Language
dc.contributor.author	Todorovic, Branimir	en
dc.contributor.author	Stanković, Miomir	en
dc.contributor.author	Moraga, Claudio	en
dc.date.accessioned	2020-12-11T13:04:36Z	-
dc.date.available	2020-12-11T13:04:36Z	-
dc.date.issued	2006-12-01	en
dc.identifier.isbn	1-4244-0433-9	en
dc.identifier.uri	http://researchrepository.mi.sanu.ac.rs/handle/123456789/4381	-
dc.description.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.	en
dc.publisher	IEEE	-
dc.relation.ispartof	8th Seminar on Neural Network Applications in Electrical Engineering, Neurel-2006 Proceedings	en
dc.subject	Divided difference filter \| Extended Kalman filter \| Gaussian sum filter \| Recurrent neural networks \| Sequential Bayesian estimation \| Unscented kalman filter	en
dc.title	Gaussian sum filters for recurrent neural networks training	en
dc.type	Conference Paper	en
dc.identifier.doi	10.1109/NEUREL.2006.341175	en
dc.identifier.scopus	2-s2.0-46749152690	en
dc.relation.firstpage	53	en
dc.relation.lastpage	57	en
item.fulltext	No Fulltext	-
item.openairetype	Conference Paper	-
item.grantfulltext	none	-
item.cerifentitytype	Publications	-
item.openairecristype	http://purl.org/coar/resource_type/c_18cf	-

1

checked on Apr 2, 2025

27

checked on Jan 31, 2025

Check