A Mean Field Theory of Layer IV of Visual Cortex and Its Application to Artificial Neural Networks
Abstract
A single cell theory for the development of selectivity and ocular dominance in visual cortex has been presented previously by Bienenstock, Cooper and Munrol. This has been extended to a network applicable to layer IV of visual cortex2 . In this paper we present a mean field approximation that captures in a fairly transparent manner the quantitative, results of the network theory. Finally, we consider the application of this theory to artificial neural networks and show that a significant reduction in architectural complexity is possible.
Cite
Text
Scofield. "A Mean Field Theory of Layer IV of Visual Cortex and Its Application to Artificial Neural Networks." Neural Information Processing Systems, 1987.Markdown
[Scofield. "A Mean Field Theory of Layer IV of Visual Cortex and Its Application to Artificial Neural Networks." Neural Information Processing Systems, 1987.](https://mlanthology.org/neurips/1987/scofield1987neurips-mean/)BibTeX
@inproceedings{scofield1987neurips-mean,
title = {{A Mean Field Theory of Layer IV of Visual Cortex and Its Application to Artificial Neural Networks}},
author = {Scofield, Christopher L.},
booktitle = {Neural Information Processing Systems},
year = {1987},
pages = {683-692},
url = {https://mlanthology.org/neurips/1987/scofield1987neurips-mean/}
}