Machine learning under resource constraints
Greffe, Nathan
Promotor(s) : Geurts, Pierre
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 |
Date of defense : | 26-Jun-2019/27-Jun-2019 |
Advisor(s) : | Geurts, Pierre |
Committee's member(s) : | Louveaux, Quentin
Louppe, Gilles Wehenkel, Louis |
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)
arch_comparison_KD.pdf
Description: improvements when using knowledge distillation
Size: 21.18 kB
Format: Adobe PDF
Description: improvements when using knowledge distillation
Size: 21.18 kB
Format: Adobe PDF
master_thesis__intro_page.pdf
Description: 1 page long Thesis summary
Size: 94.9 kB
Format: Adobe PDF
Description: 1 page long Thesis summary
Size: 94.9 kB
Format: Adobe PDF
arch_comparison_SE.pdf
Description: improvements when adding Squeeze-and-Excitation blocks
Size: 31.89 kB
Format: Adobe PDF
Description: improvements when adding Squeeze-and-Excitation blocks
Size: 31.89 kB
Format: Adobe PDF
pruning_cmparison.pdf
Description: comparison between the different pruning algorithms
Size: 32.12 kB
Format: Adobe PDF
Description: comparison between the different pruning algorithms
Size: 32.12 kB
Format: Adobe PDF
Cite this master thesis
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.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.