Adaptation in a deep network

Show simple record

dc.contributor.advisor Pillow, Jonathan W.
dc.contributor.advisor Miikkulainen, Risto
dc.creator Ruiz, Vito Manuel
dc.date.accessioned 2011-07-08T20:07:14Z
dc.date.available 2011-07-08T20:07:14Z
dc.date.created 2011-05
dc.date.issued 2011-07-08
dc.date.submitted May 2011
dc.identifier.uri http://hdl.handle.net/2152/ETD-UT-2011-05-3156
dc.description.abstract Though adaptational effects are found throughout the visual system, the underlying mechanisms and benefits of this phenomenon are not yet known. In this work, the visual system is modeled as a Deep Belief Network, with a novel “post-training” paradigm (i.e. training the network further on certain stimuli) used to simulate adaptation in vivo. An optional sparse variant of the DBN is used to help bring about meaningful and biologically relevant receptive fields, and to examine the effects of sparsification on adaptation in their own right. While results are inconclusive, there is some evidence of an attractive bias effect in the adapting network, whereby the network’s representations are drawn closer to the adapting stimulus. As a similar attractive bias is documented in human perception as a result of adaptation, there is thus evidence that the statistical properties underlying the adapting DBN also have a role in the adapting visual system, including efficient coding and optimal information transfer given limited resources. These results are irrespective of sparsification. As adaptation has never been tested directly in a neural network, to the author’s knowledge, this work sets a precedent for future experiments.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.subject Deep belief network
dc.subject Neural network
dc.subject Generative model
dc.subject Adaptation
dc.subject Vision
dc.subject Efficient coding
dc.subject Sight
dc.title Adaptation in a deep network
dc.date.updated 2011-07-08T20:07:26Z
dc.identifier.slug 2152/ETD-UT-2011-05-3156
dc.contributor.committeeMember Fiete, Ila
dc.contributor.committeeMember Geisler, Wilson
dc.contributor.committeeMember Seidemann, Eyal
dc.description.department Neuroscience
dc.type.genre thesis
dc.type.material text
thesis.degree.department Neuroscience
thesis.degree.discipline Neuroscience
thesis.degree.grantor University of Texas at Austin
thesis.degree.level Masters
thesis.degree.name Master of Science in Neuroscience

Files in this work

Download File: RUIZ-THESIS.pdf
Size: 2.375Mb
Format: application/pdf

This work appears in the following Collection(s)

Show simple record


Advanced Search

Browse

My Account

Statistics

Information