HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Theses

Representation Learning and Deep Generative Modeling in Dynamical Systems

Jean-Yves Franceschi 1
1 MLIA - Machine Learning and Information Access
ISIR - Institut des Systèmes Intelligents et de Robotique
Abstract : The recent rise of deep learning has been motivated by numerous scientific breakthroughs, particularly regarding representation learning and generative modeling. However, most of these achievements have been obtained on image or text data, whose evolution through time remains challenging for existing methods. Given their importance for autonomous systems to adapt in a constantly evolving environment, these challenges have been actively investigated in a growing body of work. In this thesis, we follow this line of work and study several aspects of temporality and dynamical systems in deep unsupervised representation learning and generative modeling. Firstly, we present a general-purpose deep unsupervised representation learning method for time series tackling scalability and adaptivity issues arising in practical applications. We then further study in a second part representation learning for sequences by focusing on structured and stochastic spatiotemporal data: videos and physical phenomena. We show in this context that performant temporal generative prediction models help to uncover meaningful and disentangled representations, and conversely. We highlight to this end the crucial role of differential equations in the modeling and embedding of these natural sequences within sequential generative models. Finally, we more broadly analyze in a third part a popular class of generative models, generative adversarial networks, under the scope of dynamical systems. We study the evolution of the involved neural networks with respect to their training time by describing it with a differential equation, allowing us to gain a novel understanding of this generative model.
Complete list of metadata

https://tel.archives-ouvertes.fr/tel-03591720
Contributor : Abes Star :  Contact
Submitted on : Monday, February 28, 2022 - 5:44:40 PM
Last modification on : Wednesday, March 2, 2022 - 3:35:44 AM

File

FRANCESCHI_Jean_Yves_these_202...
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-03591720, version 1

Citation

Jean-Yves Franceschi. Representation Learning and Deep Generative Modeling in Dynamical Systems. Machine Learning [cs.LG]. Sorbonne Université, 2022. English. ⟨NNT : 2022SORUS014⟩. ⟨tel-03591720⟩

Share

Metrics

Record views

261

Files downloads

115