Comparing linear structure-based and data-driven latent spatial representations for sequence prediction

Myriam Bontonou; Carlos Lassance; Vincent Gripon; Nicolas Farrugia

doi:10.1117/12.2528450

Conference papers

Comparing linear structure-based and data-driven latent spatial representations for sequence prediction

Myriam Bontonou ^{1, 2, 3} Carlos Lassance ^{1, 2, 3} Vincent Gripon ^{1, 2, 3} Nicolas Farrugia ^{1, 2}

1 Lab-STICC_IMTA_CACS_IAS

Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance

2 IMT Atlantique - ELEC - Département Electronique

3 MILA - Montreal Institute for Learning Algorithms [Montréal]

Keywords : Sequence Prediction Auto-Encoders Graph-supported Time Series Spatio-temporal Sequences Graph Signal Processing Latent Representations

Document type :

Conference papers

Domain :

Computer Science [cs] / Signal and Image Processing

Computer Science [cs] / Machine Learning [cs.LG]

Complete list of metadata

Cited literature [24 references] Display Hide Download

https://hal-imt-atlantique.archives-ouvertes.fr/hal-02189734
Contributor : Myriam Bontonou Connect in order to contact the contributor
Submitted on : Friday, July 19, 2019 - 9:59:22 PM
Last modification on : Friday, August 5, 2022 - 2:54:52 PM

Comparing linear structure-based and data-driven latent spatial representations for sequence prediction

Files

Identifiers

Collections

Citation

Export

Metrics

28

76

Comparing linear structure-based and data-driven latent spatial representations for sequence prediction

Files

Identifiers

Collections

Citation

Export

Share

Metrics

28

76