Linear dynamical based models for sequential domains

Luca Pasa, Alessandro Sperduti, Peter Tino

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The aim of the paper is to explore how models based on a linear dynamic can be used in order to perform a prediction task in sequential domains. In the literature, it has already been shown that Linear Dynamical Systems (LDSs) can be quite useful when dealing with sequence learning tasks. Our aim is to study whether it is possible to use LDSs as building blocks for constructing more complex and powerful models. Specifically, we propose a model dubbed Linear System Network, that exploits several LDSs in order to compute a nonlinear projection of the input. Moreover, we explore whether is it possible to apply a co-learning technique in order to improve the performance of LDSs for the considered prediction task.

Original languageEnglish
Title of host publication2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages2201-2208
Number of pages8
Volume2017-May
ISBN (Electronic)9781509061815
DOIs
Publication statusE-pub ahead of print - 3 Jul 2017
Event2017 International Joint Conference on Neural Networks, IJCNN 2017 - Anchorage, United States
Duration: 14 May 201719 May 2017

Conference

Conference2017 International Joint Conference on Neural Networks, IJCNN 2017
Country/TerritoryUnited States
CityAnchorage
Period14/05/1719/05/17

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Linear dynamical based models for sequential domains'. Together they form a unique fingerprint.

Cite this