Model Matching and SFMD Computation
Abstract
In systems that process sensory data there is frequently a model matching stage where class hypotheses are combined to recognize a complex entity. We introduce a new model of parallelism, the Single Function Multiple Data (SFMD) model, appropriate to this stage. SFMD functionality can be added with small hardware expense to certain existing SIMD architectures, and as an incremental addition to the programming model. Adding SFMD to an SIMD machine will not only allow faster model matching, but also increase its flexibility as a general purpose machine and its scope in performing the initial stages of sensory processing.
Cite
Text
Rehfuss and Hammerstrom. "Model Matching and SFMD Computation." Neural Information Processing Systems, 1995.Markdown
[Rehfuss and Hammerstrom. "Model Matching and SFMD Computation." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/rehfuss1995neurips-model/)BibTeX
@inproceedings{rehfuss1995neurips-model,
title = {{Model Matching and SFMD Computation}},
author = {Rehfuss, Steven and Hammerstrom, Dan W.},
booktitle = {Neural Information Processing Systems},
year = {1995},
pages = {713-719},
url = {https://mlanthology.org/neurips/1995/rehfuss1995neurips-model/}
}