ML Anthology

On the Effect of Analog Noise in Discrete-Time Analog Computations

Wolfgang Maass, Pekka Orponen
NeCo 1998 pp. 1071-1095
doi:10.1162/089976698300017359 /neco/1998/maass1998neco-effect/

Abstract

We introduce a model for analog computation with discrete time in the presence of analog noise that is flexible enough to cover the most important concrete cases, such as noisy analog neural nets and networks of spiking neurons. This model subsumes the classical model for digital computation in the presence of noise. 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.

PDF NeCo Semantic Scholar

Cite

Text

Maass and Orponen. "On the Effect of Analog Noise in Discrete-Time Analog Computations." Neural Computation, 1998. doi:10.1162/089976698300017359

Markdown

[Maass and Orponen. "On the Effect of Analog Noise in Discrete-Time Analog Computations." Neural Computation, 1998.](https://mlanthology.org/neco/1998/maass1998neco-effect/) doi:10.1162/089976698300017359

BibTeX

@article{maass1998neco-effect,
  title     = {{On the Effect of Analog Noise in Discrete-Time Analog Computations}},
  author    = {Maass, Wolfgang and Orponen, Pekka},
  journal   = {Neural Computation},
  year      = {1998},
  pages     = {1071-1095},
  doi       = {10.1162/089976698300017359},
  volume    = {10},
  url       = {https://mlanthology.org/neco/1998/maass1998neco-effect/}
}