Abstract
Stochastic computing is a low cost, noise tolerant computing technique based on streams of random bits. Given the non-deterministic nature of the architecture, we apply information theoretic techniques to the analysis and design of stochastic circuits. The fundamental circuit elements, adders and multipliers, are characterized in terms of mutual information between the desired quantity and the stochastic output. Using this measure we verify that stochastic computations are tolerant to errors caused by unreliable hardware. A surprising observation is that for two-input single-output stochastic adders and multipliers, it is better to have two noise sources at the inputs than a single noise source at the output.
Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
