Adaptation in a deep network

Show full record

Title: Adaptation in a deep network
Author: Ruiz, Vito Manuel
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.
Department: Neuroscience
Subject: Deep belief network Neural network Generative model Adaptation Vision Efficient coding Sight
URI: http://hdl.handle.net/2152/ETD-UT-2011-05-3156
Date: 2011-05

Files in this work

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

This work appears in the following Collection(s)

Show full record


Advanced Search

Browse

My Account

Statistics

Information