Performance of Connectionist Learning Algorithms on 2-D SIMD Processor Arrays
Abstract
The mapping of the back-propagation and mean field theory learning algorithms onto a generic 2-D SIMD computer is described. This architecture proves to be very adequate for these applications since efficiencies close to the optimum can be attained. Expressions to find the learning rates are given and then particularized to the DAP array procesor.
Cite
Text
Nuñez and Fortes. "Performance of Connectionist Learning Algorithms on 2-D SIMD Processor Arrays." Neural Information Processing Systems, 1989.Markdown
[Nuñez and Fortes. "Performance of Connectionist Learning Algorithms on 2-D SIMD Processor Arrays." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/nunez1989neurips-performance/)BibTeX
@inproceedings{nunez1989neurips-performance,
title = {{Performance of Connectionist Learning Algorithms on 2-D SIMD Processor Arrays}},
author = {Nuñez, Fernando J. and Fortes, José A. B.},
booktitle = {Neural Information Processing Systems},
year = {1989},
pages = {810-817},
url = {https://mlanthology.org/neurips/1989/nunez1989neurips-performance/}
}