Skip to Main content Skip to Navigation
Theses

Towards efficient learning of graphical models and neural networks with variational techniques

Abstract : In this thesis, I will mainly focus on variational inference and probabilistic models. In particular, I will cover several projects I have been working on during my PhD about improving the efficiency of AI/ML systems with variational techniques. The thesis consists of two parts. In the first part, the computational efficiency of probabilistic graphical models is studied. In the second part, several problems of learning deep neural networks are investigated, which are related to either energy efficiency or sample efficiency
Document type :
Theses
Complete list of metadatas

Cited literature [389 references]  Display  Hide  Download

https://pastel.archives-ouvertes.fr/tel-02919022
Contributor : Abes Star :  Contact
Submitted on : Friday, August 21, 2020 - 2:42:08 PM
Last modification on : Wednesday, October 14, 2020 - 4:11:13 AM

File

TH2019PESC1037.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02919022, version 1

Collections

Citation

Xu Hu. Towards efficient learning of graphical models and neural networks with variational techniques. Artificial Intelligence [cs.AI]. Université Paris-Est, 2019. English. ⟨NNT : 2019PESC1037⟩. ⟨tel-02919022⟩

Share

Metrics

Record views

78

Files downloads

49