On the Effect of Analog Noise in Discrete-Time Analog Computations
Abstract
We introduce a model for noise-robust analog computations with discrete time that is flexible enough to cover the most important concrete cases, such as computations in noisy analog neural nets and networks of noisy spiking neurons. We show that the presence of arbitrarily small amounts of analog noise reduces the power of analog computational models to that of finite automata, and we also prove a new type of upper bound for the VC-dimension of computational models with analog noise.
Cite
Text
Maass and Orponen. "On the Effect of Analog Noise in Discrete-Time Analog Computations." Neural Information Processing Systems, 1996.Markdown
[Maass and Orponen. "On the Effect of Analog Noise in Discrete-Time Analog Computations." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/maass1996neurips-effect/)BibTeX
@inproceedings{maass1996neurips-effect,
title = {{On the Effect of Analog Noise in Discrete-Time Analog Computations}},
author = {Maass, Wolfgang and Orponen, Pekka},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {218-224},
url = {https://mlanthology.org/neurips/1996/maass1996neurips-effect/}
}