Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 292 | DOWNLOAD 1060

Machine learning under resource constraints

Download
Greffe, Nathan ULiège
Promotor(s) : Geurts, Pierre ULiège
Date of defense : 26-Jun-2019/27-Jun-2019 • Permalink : http://hdl.handle.net/2268.2/6798
Details
Title : Machine learning under resource constraints
Translated title : [fr] apprentissage inductif avec ressources limitées
Author : Greffe, Nathan ULiège
Date of defense  : 26-Jun-2019/27-Jun-2019
Advisor(s) : Geurts, Pierre ULiège
Committee's member(s) : Louveaux, Quentin ULiège
Louppe, Gilles ULiège
Wehenkel, Louis ULiège
Language : English
Number of pages : 78
Keywords : [fr] machine learning
[fr] deep learning
Discipline(s) : Engineering, computing & technology > Computer science
Target public : Researchers
Professionals of domain
Student
Complementary URL : https://github.com/NatGr/Master_Thesis
Institution(s) : Université de Liège, Liège, Belgique
Degree: Master en ingénieur civil en informatique, à finalité spécialisée en "intelligent systems"
Faculty: Master thesis of the Faculté des Sciences appliquées

Abstract

[fr] This master thesis has for objective to explore different techniques (architecture, pruning as an architecture search, knowledge distillation, quantization) to improve the inference time of convolutionnal neural networks performing image classification on an embedded device.


File(s)

Document(s)

File
Access arch_comparison_KD.pdf
Description: improvements when using knowledge distillation
Size: 21.18 kB
Format: Adobe PDF
File
Access master_thesis__intro_page.pdf
Description: 1 page long Thesis summary
Size: 94.9 kB
Format: Adobe PDF
File
Access arch_comparison_SE.pdf
Description: improvements when adding Squeeze-and-Excitation blocks
Size: 31.89 kB
Format: Adobe PDF
File
Access arch_comparison.pdf
Description: vanilla architectures comparison
Size: 31.79 kB
Format: Adobe PDF
File
Access master_thesis__report.pdf
Description: Thesis report
Size: 4.08 MB
Format: Adobe PDF
File
Access pruning_cmparison.pdf
Description: comparison between the different pruning algorithms
Size: 32.12 kB
Format: Adobe PDF

Author

  • Greffe, Nathan ULiège Université de Liège > Master ingé. civ. info., à fin.

Promotor(s)

Committee's member(s)

  • Louveaux, Quentin ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation : Optimisation discrète
    ORBi View his publications on ORBi
  • Louppe, Gilles ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data
    ORBi View his publications on ORBi
  • Wehenkel, Louis ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
    ORBi View his publications on ORBi
  • Total number of views 292
  • Total number of downloads 1060










All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.