Retinotopic Preservation in Deep Belief Network Visual Learning

dc.comment.hiddenImage of neuron and visual pathway are public domainen
dc.contributor.authorLam, Michael
dc.date.accessioned2011-04-29T18:16:24Z
dc.date.available2011-04-29T18:16:24Z
dc.date.issued2011-04-29T18:16:24Z
dc.date.submitted2011
dc.description.abstractOne of the foremost characteristics of the mammalian visual system is the retinotopic mapping observed in the low-level visual processing centres; the spatial pattern of activation in the lateral geniculate nucleus and primary visual cortex corresponds topologically to the pattern of light falling on the retina. Various vision systems have been developed that take advantage of structured input such as retinotopy, however these systems are often not biologically plausible. Using a parsimonious approach for implementing retinotopy, one that is based on the biology of our visual pathway, we run simulations of visual learning using a deep belief network (DBN). Experiments show that we can successfully produce receptive fields and activation maps typical of the LGN and visual cortex respectively. These results may indicate a possible avenue of exploration into discovering the workings of the early visual system (and possibly more) on a neuronal level.en
dc.identifier.urihttp://hdl.handle.net/10012/5894
dc.language.isoenen
dc.pendingfalseen
dc.publisherUniversity of Waterlooen
dc.subjectVisual Learningen
dc.subjectDBNen
dc.subjectRetinotopyen
dc.subject.programComputer Scienceen
dc.titleRetinotopic Preservation in Deep Belief Network Visual Learningen
dc.typeMaster Thesisen
uws-etd.degreeMaster of Mathematicsen
uws-etd.degree.departmentSchool of Computer Scienceen
uws.peerReviewStatusUnrevieweden
uws.scholarLevelGraduateen
uws.typeOfResourceTexten

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Lam_Michael.pdf
Size:
2.46 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
245 B
Format:
Item-specific license agreed upon to submission
Description: