UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Ocular Dominance and Patterned Lateral Connections in a Self-Organizing Model of the Primary Visual Cortex (1995)
Joseph Sirosh
and
Risto Miikkulainen
A neural network model for the self-organization of ocular dominance and lateral connections from binocular input is presented. The self-organizing process results in a network where (1) afferent weights of each neuron organize into smooth hill-shaped receptive fields primarily on one of the retinas, (2) neurons with common eye preference form connected, intertwined patches, and (3) lateral connections primarily link regions of the same eye preference. Similar self-organization of cortical structures has been observed experimentally in strabismic kittens. The model shows how patterned lateral connections in the cortex may develop based on correlated activity and explains why lateral connection patterns follow receptive field properties such as ocular dominance.
View:
PDF
,
PS
Citation:
In
Advances in Neural Information Processing Systems 7
, Gerald Tesauro and David S. Touretzky and Todd K. Leen (Eds.), pp. 109-116 1995. Cambridge, MA: MIT Press.
Bibtex:
@InProceedings{sirosh:nips7, title={Ocular Dominance and Patterned Lateral Connections in a Self-Organizing Model of the Primary Visual Cortex}, author={Joseph Sirosh and Risto Miikkulainen}, booktitle={Advances in Neural Information Processing Systems 7}, editor={Gerald Tesauro and David S. Touretzky and Todd K. Leen}, publisher={Cambridge, MA: MIT Press}, pages={109-116}, url="http://www.cs.utexas.edu/users/ai-lab?sirosh:nips94", year={1995} }
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Joseph Sirosh
Ph.D. Alumni
joseph sirosh [at] gmail com
Areas of Interest
Brain and Cognitive Disorders
Computational Neuroscience
Visual Cortex
Labs
Neural Networks