Réseaux convolutifs à politiques

Authors: Pothier, Dominique
Advisor: Lamontagne, Luc
Abstract: Despite their excellent performances, artificial neural networks high demand of both data and computational power limit their adoption in many domains. Developing less demanding architecture thus remain an important endeavor. This thesis seeks to produce a more flexible and less resource-intensive architecture by using reinforcement learning theory. When considering a network as an agent instead of a function approximator, one realize that the implicit policy followed by popular feed forward networks is extremely simple. We hypothesize that an architecture able to learn a more flexible policy could reach similar performances while reducing its resource footprint. The architecture we propose is inspired by research done in weight prediction, particularly by the hypernetwork architecture, which we use as a baseline model.Our results show that learning a dynamic policy achieving similar results to the static policies of conventional networks is not a trivial task. Our proposed architecture succeeds in limiting its parameter space by 20%, but does so at the cost of a 24% computation increase and loss of5% accuracy. Despite those results, we believe that this architecture provides a baseline that can be improved in multiple ways that we describe in the conclusion.
Document Type: Mémoire de maîtrise
Issue Date: 2021
Open Access Date: 24 May 2021
Permalink: http://hdl.handle.net/20.500.11794/69184
Grantor: Université Laval
Collection:Thèses et mémoires

Files in this item:
Description SizeFormat 
36989.pdf1.14 MBAdobe PDFThumbnail
View/Open
All documents in CorpusUL are protected by Copyright Act of Canada.