VLSI Implementation of Cortical Visual Motion Detection Using an Analog Neural Computer
Abstract
Two dimensional image motion detection neural networks have been implemented using a general purpose analog neural computer. The neural circuits perform spatiotemporal feature extraction based on the cortical motion detection model of Adelson and Bergen. The neural computer provides the neurons, synapses and synaptic time-constants required to realize the model in VLSI hardware. Results show that visual motion estimation can be implemented with simple sum-and(cid:173) threshold neural hardware with temporal computational capabilities. The neural circuits compute general 20 visual motion in real-time.
Cite
Text
Etienne-Cummings et al. "VLSI Implementation of Cortical Visual Motion Detection Using an Analog Neural Computer." Neural Information Processing Systems, 1996.Markdown
[Etienne-Cummings et al. "VLSI Implementation of Cortical Visual Motion Detection Using an Analog Neural Computer." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/etiennecummings1996neurips-vlsi/)BibTeX
@inproceedings{etiennecummings1996neurips-vlsi,
title = {{VLSI Implementation of Cortical Visual Motion Detection Using an Analog Neural Computer}},
author = {Etienne-Cummings, Ralph and Van der Spiegel, Jan and Takahashi, Naomi and Apsel, Alyssa and Mueller, Paul},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {685-691},
url = {https://mlanthology.org/neurips/1996/etiennecummings1996neurips-vlsi/}
}