Abstract
Stochastic Computing (SC) essentially represents numbers as streams of random bits and reconstructs numbers by calculating frequencies. It employs random bits to calculate via simpler circuits and with greater tolerance for errors. As a computing paradigm, SC is currently undergoing a revival. Since stochastic circuits have a small size, SC has regained interest recently due to its potential usage in some emerging nanotechnologies. In this paper, we briefly present stochastic computing and discuss its applications, benefits, and challenges.
Highlights
The continuing capability of manufacturers to produce smaller devices with each technology generation has resulted in exponentially increasing circuit density structures
There is a need for unconventional computing methods that directly address these issues
Stochastic computing can be seen as an alternative to conventional real arithmetic. It is an unconventional computing technique originally proposed to reduce the size of the digital arithmetic circuit
Summary
The continuing capability of manufacturers to produce smaller devices with each technology generation has resulted in exponentially increasing circuit density structures. As semiconductor technology approaches the deep nanoscale regime, the stochasticity of the device and circuit fabric will need to be addressed. In the 1960s, Stochastic Computing (SC) was proposed as a low-cost alternative to conventional binary computing. It performs operations using probability [1] instead of arithmetic. The stochastic computer has similarities to both analog and digital computers, it is fundamentally different from both. It is uniquely different in that it represents and processes information in the form of digitized probabilities
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
