Bayesian Inference for Training of Long Short Term Memory Models in Chaotic Time Series Forecasting

Cristian Rodríguez Rivero, Julián Pucheta, Daniel Patiño, Jose Luis Puglisi, Paula Otaño, Leonardo Franco, Gustavo Juarez, Efrén Gorrostieta, Alvaro David Orjuela-Cañón

Research output: Chapter in Book/InformChapterResearch

1 Scopus citations

Abstract

For time series forecasting, obtaining models is based on the use of past observations from the same sequence. In those cases, when the model is learning from data, there is not an extra information that discuss about the quantity of noise inside the data available. In practice, it is necessary to deal with finite noisy datasets, which lead to uncertainty about the propriety of the model. For this problem, the employment of the Bayesian inference tools are preferable. A modified algorithm used for training a long-short term memory recurrent neural network for time series forecasting is presented. This approach was chosen to improve the forecasting of the original series, employing an implementation based on the minimization of the associated Kullback-Leibler Information Criterion. For comparison, a nonlinear autoregressive model implemented with a feedforward neural network was also presented. A simulation study was conducted to evaluate and illustrate results, comparing this approach with Bayesian neural-networks-based algorithms for artificial chaotic time-series and showing an improvement in terms of forecasting errors.

Original languageEnglish (US)
Title of host publicationApplications of Computational Intelligence - 2nd IEEE Colombian Conference, ColCACI 2019, Revised Selected Papers
EditorsAlvaro David Orjuela-Cañón, Juan Carlos Figueroa-García, Julián David Arias-Londoño
PublisherSpringer
Pages197-208
Number of pages12
ISBN (Print)9783030362102
DOIs
StatePublished - Dec 5 2019
Event2nd IEEE Colombian Conference on Applications in Computational Intelligence, ColCACI 2019 - Barranquilla, Colombia
Duration: Jun 5 2019Jun 7 2019

Publication series

NameCommunications in Computer and Information Science
Volume1096 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference2nd IEEE Colombian Conference on Applications in Computational Intelligence, ColCACI 2019
Country/TerritoryColombia
CityBarranquilla
Period6/5/196/7/19

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'Bayesian Inference for Training of Long Short Term Memory Models in Chaotic Time Series Forecasting'. Together they form a unique fingerprint.

Cite this