Reverted good faith edits by Mhn18820: You cannot copy, even with a refernce, in this way form http://cctbio.ece.umn.edu/wiki/images/e/ec/Najafi_Lilja_Riedel_Bazargan_Polysynchronous_Stochastic_Circuits.pdf. (TW)
</ref> More recently, stochastic circuits have been successfully used in [[image processing]] tasks such as [[edge detection]].
<ref>{{Cite book | last1 = Alaghi | first1 = A. | last2 = Li | first2 = C. | last3 = Hayes | first3 = J. P. | doi = 10.1145/2463209.2488901 | chapter = Stochastic circuits for real-time image-processing applications | title = Proceedings of the 50th Annual Design Automation Conference on - DAC '13 | pages = 1 | year = 2013 | isbn = 9781450320719 | pmid = | pmc = }}</ref> and [[Thresholding_(image_processing) | image thresholding]] <ref>{{Cite book | last1 = Najafi| first1 = M. H. | last2 = Salehi | first2 = M. E. Salehi | doi = 10.1109/TVLSI.2015.2415932 | chapter = A Fast Fault-Tolerant Architecture for Sauvola Local Image Thresholding Algorithm Using Stochastic Computing | title = IEEE Transactions on Very Large Scale Integration (VLSI) Systems - TVLSI '16 | pages = 5 | year = 2016 | issn = 1063-8210| pmid = | pmc = }}</ref>.
== Strengths and weaknesses ==
Line 172:
bits in a stream are flipped, those errors will have no significant impact
on the solution.
A more compelling advantage still of the stochastic paradigm is that, with a stochastic representation, computational units can tolerate skew in the arrival time of their inputs. This stems from the fact that the stochastic representation is uniform: all that matters in terms of the value that is computed is the number of ones in the bit stream or the fraction of time that the signal is high. The correct value is computed even when the inputs are misaligned temporally. Accordingly, adopting the stochastic paradigm obviates the need for a global clock signal and the associated clock distribution network. Instead one can simply use local clock signal generators throughout <ref>{{Cite journal | last1 = Najafi | first1 = M. H. | last2 = Lilja | first2 = D. J. | last3 = Riedel| first3 = M. D. | last4 = Bazargan | first4 = K. | doi = 10.1109/ASPDAC.2016.7428060 | title = Polysynchronous stochastic circuits | journal = 2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC) | year = 2016 | pmid = | pmc = }}</ref>.
[[File:Polysynchronous-AND.png|frame|center|Stochastic multiplication using an AND gate with unsynchronized random bit streams.]]
Finally, stochastic computing provides an estimate of the solution
