Simulation of the Neocognitron on a CCD Parallel Processing Architecture
Abstract
The neocognitron is a neural network for pattern recognition and feature extraction. An analog CCD parallel processing architecture developed at Lincoln Laboratory is particularly well suited to the computational re(cid:173) quirements of shared-weight networks such as the neocognitron, and imple(cid:173) mentation of the neocognitron using the CCD architecture was simulated. A modification to the neocognitron training procedure, which improves network performance under the limited arithmetic precision that would be imposed by the CCD architecture, is presented.
Cite
Text
Chuang and Chiang. "Simulation of the Neocognitron on a CCD Parallel Processing Architecture." Neural Information Processing Systems, 1990.Markdown
[Chuang and Chiang. "Simulation of the Neocognitron on a CCD Parallel Processing Architecture." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/chuang1990neurips-simulation/)BibTeX
@inproceedings{chuang1990neurips-simulation,
title = {{Simulation of the Neocognitron on a CCD Parallel Processing Architecture}},
author = {Chuang, Michael L. and Chiang, Alice M.},
booktitle = {Neural Information Processing Systems},
year = {1990},
pages = {1039-1045},
url = {https://mlanthology.org/neurips/1990/chuang1990neurips-simulation/}
}