An energy-based deep splitting method for the nonlinear filtering problem

CC BY

Saved in:
Bibliographic Details
Main Authors: Kasper, Bågmark, Adam, Andersson, Stig, Larsson
Format: Book
Language:English
Published: Springer 2023
Subjects:
Online Access:https://link.springer.com/article/10.1007/s42985-023-00231-5
https://dlib.phenikaa-uni.edu.vn/handle/PNK/7603
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-7603
record_format dspace
spelling oai:localhost:PNK-76032023-04-06T01:56:30Z An energy-based deep splitting method for the nonlinear filtering problem Kasper, Bågmark Adam, Andersson Stig, Larsson Zakai equatio energy-based deep splitting method CC BY The purpose of this paper is to explore the use of deep learning for the solution of the nonlinear filtering problem. This is achieved by solving the Zakai equation by a deep splitting method, previously developed for approximate solution of (stochastic) partial differential equations. This is combined with an energy-based model for the approximation of functions by a deep neural network. This results in a computationally fast filter that takes observations as input and that does not require re-training when new observations are received. The method is tested on four examples, two linear in one and twenty dimensions and two nonlinear in one dimension. The method shows promising performance when benchmarked against the Kalman filter and the bootstrap particle filter. 2023-04-06T01:56:30Z 2023-04-06T01:56:30Z 2023 Book https://link.springer.com/article/10.1007/s42985-023-00231-5 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7603 en application/pdf Springer
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic Zakai equatio
energy-based deep splitting method
spellingShingle Zakai equatio
energy-based deep splitting method
Kasper, Bågmark
Adam, Andersson
Stig, Larsson
An energy-based deep splitting method for the nonlinear filtering problem
description CC BY
format Book
author Kasper, Bågmark
Adam, Andersson
Stig, Larsson
author_facet Kasper, Bågmark
Adam, Andersson
Stig, Larsson
author_sort Kasper, Bågmark
title An energy-based deep splitting method for the nonlinear filtering problem
title_short An energy-based deep splitting method for the nonlinear filtering problem
title_full An energy-based deep splitting method for the nonlinear filtering problem
title_fullStr An energy-based deep splitting method for the nonlinear filtering problem
title_full_unstemmed An energy-based deep splitting method for the nonlinear filtering problem
title_sort energy-based deep splitting method for the nonlinear filtering problem
publisher Springer
publishDate 2023
url https://link.springer.com/article/10.1007/s42985-023-00231-5
https://dlib.phenikaa-uni.edu.vn/handle/PNK/7603
_version_ 1762456091040415744
score 8.891053