Show simple item record

dc.contributor.authorNagisetty, Vineel
dc.date.accessioned2021-08-26 20:31:14 (GMT)
dc.date.available2021-08-26 20:31:14 (GMT)
dc.date.issued2021-08-26
dc.date.submitted2021-08-16
dc.identifier.urihttp://hdl.handle.net/10012/17272
dc.description.abstractThe extensive impact of Deep Neural Networks (DNNs) on various industrial applications and research areas within the last decade can not be overstated. However, they are also subject to notable limitations, namely their vulnerability to various forms of security attacks and their need for excessive data - especially for particular types of DNNs such as generative adversarial networks (GANs). Tackling the former challenge, researchers have proposed several testing, analysis, and verification (TAV) methods for DNNs. However, current state-of-the-art DNN TAV methods are either not scalable to industrial-sized DNNs or are not expressible (i.e. can not test DNNs for a rich set of properties). On the other hand, making GANs more data-efficient is an open area of research, and can potentially lead to improvements in training time and costs. In this work, I address these issues by leveraging domain knowledge - task-specific knowledge provided as an additional source of information - in order to better test and train DNNs. In particular, I present Constrained Gradient Descent (CGD), a novel algorithm (and a resultant tool called CGDTest) that leverages domain knowledge (in the form of logical constraints) to create a DNN TAV method that is both scalable and expressible. Further, I introduce a novel gradient descent method (and a resultant GAN referred to as xAI-GAN) that leverages domain knowledge (provided in the form of neuron importance) to train GANs to be more data-efficient. Through empirical evaluation, I show that both tools improve over current state-of-the-art methods in their respective applications. This thesis highlights the potential of leveraging domain knowledge to mitigate DNN weaknesses and paves the way for further research in this area.en
dc.language.isoenen
dc.publisherUniversity of Waterlooen
dc.subjectdeep neural networksen
dc.subjectDNN testing and verificationen
dc.subjectdomain knowledgeen
dc.subjectgenerative adversarial networksen
dc.titleDomain Knowledge Guided Testing and Training of Neural Networksen
dc.typeMaster Thesisen
dc.pendingfalse
uws-etd.degree.departmentElectrical and Computer Engineeringen
uws-etd.degree.disciplineElectrical and Computer Engineeringen
uws-etd.degree.grantorUniversity of Waterlooen
uws-etd.degreeMaster of Applied Scienceen
uws-etd.embargo.terms0en
uws.contributor.advisorGanesh, Vijay
uws.contributor.affiliation1Faculty of Engineeringen
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws.typeOfResourceTexten
uws.peerReviewStatusUnrevieweden
uws.scholarLevelGraduateen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record


UWSpace

University of Waterloo Library
200 University Avenue West
Waterloo, Ontario, Canada N2L 3G1
519 888 4883

All items in UWSpace are protected by copyright, with all rights reserved.

DSpace software

Service outages