UWSpace is currently experiencing technical difficulties resulting from its recent migration to a new version of its software. These technical issues are not affecting the submission and browse features of the site. UWaterloo community members may continue submitting items to UWSpace. We apologize for the inconvenience, and are actively working to resolve these technical issues.
 

Retinotopic Preservation in Deep Belief Network Visual Learning

Thumbnail Image

Files

Lam_Michael.pdf (2.46 MB)

Date

2011-04-29T18:16:24Z

Authors

Lam, Michael

Journal Title

Journal ISSN

Volume Title

Publisher

University of Waterloo

Abstract

One 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.

Description

Keywords

Visual Learning, DBN, Retinotopy

LC Keywords

Citation

URI

http://hdl.handle.net/10012/5894

Collections

Theses
Computer Science