English

Neural Networks Built from Unreliable Components

Neural and Evolutionary Computing 2013-06-04 v4 Information Theory math.IT

Abstract

Recent advances in associative memory design through strutured pattern sets and graph-based inference algorithms have allowed the reliable learning and retrieval of an exponential number of patterns. Both these and classical associative memories, however, have assumed internally noiseless computational nodes. This paper considers the setting when internal computations are also noisy. Even if all components are noisy, the final error probability in recall can often be made exceedingly small, as we characterize. There is a threshold phenomenon. We also show how to optimize inference algorithm parameters when knowing statistical properties of internal noise.

Keywords

Cite

@article{arxiv.1301.6265,
  title  = {Neural Networks Built from Unreliable Components},
  author = {Amin Karbasi and Amir Hesam Salavati and Amin Shokrollahi and Lav Varshney},
  journal= {arXiv preprint arXiv:1301.6265},
  year   = {2013}
}

Comments

This paper has been withdrawn by the author due to some personal restrictions on the publication policy

R2 v1 2026-06-21T23:15:46.677Z