Show simple item record

dc.contributor.authorDutta, Shamak
dc.date.accessioned2019-08-28 13:53:08 (GMT)
dc.date.available2019-08-28 13:53:08 (GMT)
dc.date.issued2019-08-28
dc.date.submitted2019-08-20
dc.identifier.urihttp://hdl.handle.net/10012/14967
dc.description.abstractThis thesis explores one of the differences between the visual cortex and deep convolutional neural networks, namely, correlated fluctuations of neuron response strength. First, we describe the similarities and differences between biological and artificial neural networks and provide motivation for bridging the gap between the two, with a focus on correlated variability. Next, we present a regularisation method for convolutional neural networks using correlated noise. The structure of the correlations are inspired from biological observations using two factors: spatial extent and tuning similarity of neurons. We provide empirical results on improved robust image classification in the setting of occluded and corrupted images. We then move on to studying the connection between popular dataset augmentation techniques and correlated variability. We compute a smooth estimate of the correlations of neural network activity as a function of distance and kernel similarity, and show the similarity to biological correlations. Finally, we introduce a structured form of Dropout for convolutional neural networks, taking into account spatial and kernel correlations. We show improvement in image classification for the VGG architecture on the CIFAR-10 dataset.en
dc.language.isoenen
dc.publisherUniversity of Waterlooen
dc.subjectDeep Learningen
dc.subjectConvolutional Neural Networksen
dc.subjectCorrelated Noiseen
dc.subjectRobust Image Classificationen
dc.titleCorrelated Noise in Deep Convolutional Neural Networksen
dc.typeMaster Thesisen
dc.pendingfalse
uws-etd.degree.departmentSystems Design Engineeringen
uws-etd.degree.disciplineSystem Design Engineeringen
uws-etd.degree.grantorUniversity of Waterlooen
uws-etd.degreeMaster of Applied Scienceen
uws.contributor.advisorTripp, Bryan
uws.contributor.advisorTaylor, Graham
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