Skip to Main content Skip to Navigation
Theses

Deep learning for multivariate time series : from vehicle control to gesture recognition and generation

Abstract : Artificial intelligence is the scientific field which studies how to create machines that are capable of intelligent behaviour. Deep learning is a family of artificial intelligence methods based on neural networks. In recent years, deep learning has lead to groundbreaking developments in the image and natural language processing fields. However, in many domains, input data consists in neither images nor text documents, but in time series that describe the temporal evolution of observed or computed quantities. In this thesis, we study and introduce different representations for time series, based on deep learning models. Firstly, in the autonomous driving domain, we show that, the analysis of a temporal window by a neural network can lead to better vehicle control results than classical approaches that do not use neural networks, especially in highly-coupled situations. Secondly, in the gesture and action recognition domain, we introduce 1D parallel convolutional neural network models. In these models, convolutions are performed over the temporal dimension, in order for the neural network to detect -and benefit from- temporal invariances. Thirdly, in the human pose motion generation domain, we introduce 2D convolutional generative adversarial neural networks where the spatial and temporal dimensions are convolved in a joint manner. Finally, we introduce an embedding where spatial representations of human poses are sorted in a latent space based on their temporal relationships.
Document type :
Theses
Complete list of metadata

https://pastel.archives-ouvertes.fr/tel-03097368
Contributor : Abes Star :  Contact Connect in order to contact the contributor
Submitted on : Tuesday, January 5, 2021 - 12:24:44 PM
Last modification on : Thursday, January 7, 2021 - 3:13:42 AM
Long-term archiving on: : Wednesday, April 7, 2021 - 9:24:48 AM

File

2020UPSLM037_archivage.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-03097368, version 1

Citation

Guillaume Devineau. Deep learning for multivariate time series : from vehicle control to gesture recognition and generation. Machine Learning [cs.LG]. Université Paris sciences et lettres, 2020. English. ⟨NNT : 2020UPSLM037⟩. ⟨tel-03097368⟩

Share

Metrics

Record views

373

Files downloads

247