Pre-Trained Neural Networks used for Non-Linear State Estimation

Enis Bayramoglu; Nils Axel Andersen; Ole Ravn; Niels Kjølstad Poulsen

doi:10.1109/ICMLA.2011.118

Pre-Trained Neural Networks used for Non-Linear State Estimation

Enis Bayramoglu, Nils Axel Andersen, Ole Ravn, Niels Kjølstad Poulsen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

487 Downloads (Pure)

Abstract

The paper focuses on nonlinear state estimation assuming non-Gaussian distributions of the states and the disturbances. The posterior distribution and the aposteriori distribution is described by a chosen family of paramtric distributions. The state transformation then results in a transformation of the paramters in the distribution. This transformation is approximated by a neural network using offline training, which is based on monte carlo sampling. In the paper, there will also be presented a method to construct a flexible distributions well suited for covering the effect of the non-linearities. The method can also be used to improve other parametric methods around regions with strong nonlinearities by including them inside the network.

Original language	English
Title of host publication	The tenth International Conference on Machine Learning and Applications
Publisher	IEEE
Publication date	2011
DOIs	https://doi.org/10.1109/ICMLA.2011.118
Publication status	Published - 2011
Event	10th International Conference on Machine Learning and Applications (ICMLA 2011) - Honolulu, Hawaii, United States Duration: 18 Dec 2011 → 21 Dec 2011 Conference number: 10

Conference

Conference	10th International Conference on Machine Learning and Applications (ICMLA 2011)
Number	10
Country/Territory	United States
City	Honolulu, Hawaii
Period	18/12/2011 → 21/12/2011

Access to Document

10.1109/ICMLA.2011.118

Prod11323338553496

http://www.icmla-conference.org/icmla11/

OpenUrl availability

Full text

Cite this

@inproceedings{6acc906f664545de96ce4616e67ed084,

title = "Pre-Trained Neural Networks used for Non-Linear State Estimation",

abstract = "The paper focuses on nonlinear state estimation assuming non-Gaussian distributions of the states and the disturbances. The posterior distribution and the aposteriori distribution is described by a chosen family of paramtric distributions. The state transformation then results in a transformation of the paramters in the distribution. This transformation is approximated by a neural network using offline training, which is based on monte carlo sampling. In the paper, there will also be presented a method to construct a flexible distributions well suited for covering the effect of the non-linearities. The method can also be used to improve other parametric methods around regions with strong nonlinearities by including them inside the network.",

author = "Enis Bayramoglu and Andersen, {Nils Axel} and Ole Ravn and Poulsen, {Niels Kj{\o}lstad}",

year = "2011",

doi = "10.1109/ICMLA.2011.118",

language = "English",

booktitle = "The tenth International Conference on Machine Learning and Applications",

publisher = "IEEE",

address = "United States",

note = "10th International Conference on Machine Learning and Applications (ICMLA 2011), ICMLA ; Conference date: 18-12-2011 Through 21-12-2011",

}

TY - GEN

T1 - Pre-Trained Neural Networks used for Non-Linear State Estimation

AU - Bayramoglu, Enis

AU - Andersen, Nils Axel

AU - Ravn, Ole

AU - Poulsen, Niels Kjølstad

N1 - Conference code: 10

PY - 2011

Y1 - 2011

N2 - The paper focuses on nonlinear state estimation assuming non-Gaussian distributions of the states and the disturbances. The posterior distribution and the aposteriori distribution is described by a chosen family of paramtric distributions. The state transformation then results in a transformation of the paramters in the distribution. This transformation is approximated by a neural network using offline training, which is based on monte carlo sampling. In the paper, there will also be presented a method to construct a flexible distributions well suited for covering the effect of the non-linearities. The method can also be used to improve other parametric methods around regions with strong nonlinearities by including them inside the network.

AB - The paper focuses on nonlinear state estimation assuming non-Gaussian distributions of the states and the disturbances. The posterior distribution and the aposteriori distribution is described by a chosen family of paramtric distributions. The state transformation then results in a transformation of the paramters in the distribution. This transformation is approximated by a neural network using offline training, which is based on monte carlo sampling. In the paper, there will also be presented a method to construct a flexible distributions well suited for covering the effect of the non-linearities. The method can also be used to improve other parametric methods around regions with strong nonlinearities by including them inside the network.

U2 - 10.1109/ICMLA.2011.118

DO - 10.1109/ICMLA.2011.118

M3 - Article in proceedings

BT - The tenth International Conference on Machine Learning and Applications

PB - IEEE

T2 - 10th International Conference on Machine Learning and Applications (ICMLA 2011)

Y2 - 18 December 2011 through 21 December 2011

ER -

Pre-Trained Neural Networks used for Non-Linear State Estimation

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this