Generalisation of a Class of Continuous Neural Networks
Abstract
We propose a way of using boolean circuits to perform real valued computation in a way that naturally extends their boolean func(cid:173) tionality. The functionality of multiple fan in threshold gates in this model is shown to mimic that of a hardware implementation of continuous Neural Networks. A Vapnik-Chervonenkis dimension and sample size analysis for the systems is performed giving best known sample sizes for a real valued Neural Network. Experimen(cid:173) tal results confirm the conclusion that the sample sizes required for the networks are significantly smaller than for sigmoidal networks.
Cite
Text
Shawe-Taylor and Zhao. "Generalisation of a Class of Continuous Neural Networks." Neural Information Processing Systems, 1995.Markdown
[Shawe-Taylor and Zhao. "Generalisation of a Class of Continuous Neural Networks." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/shawetaylor1995neurips-generalisation/)BibTeX
@inproceedings{shawetaylor1995neurips-generalisation,
title = {{Generalisation of a Class of Continuous Neural Networks}},
author = {Shawe-Taylor, John and Zhao, Jieyu},
booktitle = {Neural Information Processing Systems},
year = {1995},
pages = {267-273},
url = {https://mlanthology.org/neurips/1995/shawetaylor1995neurips-generalisation/}
}