|
Digital Library of the
European Council for Modelling and Simulation |
Title: |
Modelling Retinal
Feature Detection With Deep Belief Networks In A Simulated Environment |
Authors: |
Diana Turcsany, Andrzej Bargiela, Tomas Maul |
Published in: |
(2014).ECMS 2014 Proceedings edited
by: Flaminio Squazzoni,
Fabio Baronio, Claudia Archetti,
Marco Castellani European Council for
Modeling and Simulation. doi:10.7148/2014 ISBN:
978-0-9564944-8-1 28th
European Conference on Modelling and Simulation, Brescia,
Italy, May 27th – 30th,
2014 |
Citation
format: |
Diana
Turcsany, Andrzej Bargiela, Tomas Maul (2014). Modelling Retinal Feature Detection With Deep Belief
Networks In A Simulated Environment, ECMS 2014 Proceedings edited by: Flaminio Squazzoni, Fabio Baronio, Claudia Archetti,
Marco Castellani European Council for Modeling and Simulation. doi:10.7148/2014-0364 |
DOI: |
http://dx.doi.org/10.7148/2014-0364 |
Abstract: |
Recent
research has demonstrated the great capability of deep belief networks for
solving a variety of visual recognition tasks. However, primary focus has
been on modelling higher level
visual features and later stages of visual processing found in the brain.
Lower level processes such as those found in the retina have gone ignored. In
this paper, we address this issue and demonstrate how the retina’s inherent
multi-layered structure lends itself naturally for modelling
with deep networks. We introduce a method for simulating the retinal
photoreceptor input and show the efficacy of deep networks in learning feature
detectors similar to retinal ganglion cells. We thereby demonstrate the
potential of deep belief networks for modelling the
earliest stages of visual processing. |
Full
text: |