Publications

BibTex format

@inproceedings{Boroumand:2021:10.1145/3394885.3431559,
author = {Boroumand, S and Bouganis, C and Constantinides, G},
doi = {10.1145/3394885.3431559},
pages = {524--529},
publisher = {ACM},
title = {Learning Boolean circuits from examples for approximate logic synthesis},
url = {http://dx.doi.org/10.1145/3394885.3431559},
year = {2021}
}

Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Many computing applications are inherently error resilient. Thus,it is possible to decrease computing accuracy to achieve greater effi-ciency in area, performance, and/or energy consumption. In recentyears, a slew of automatic techniques for approximate computinghas been proposed; however, most of these techniques require fullknowledge of an exact, or ‘golden’ circuit description. In contrast,there has been significant recent interest in synthesizing computa-tion from examples, a form of supervised learning. In this paper, weexplore the relationship between supervised learning of Booleancircuits and existing work on synthesizing incompletely-specifiedfunctions. We show that when considered through a machine learn-ing lens, the latter work provides a good training accuracy butpoor test accuracy. We contrast this with prior work from the 1990swhich uses mutual information to steer the search process, aimingfor good generalization. By combining this early work with a recentapproach to learning logic functions, we are able to achieve a scal-able and efficient machine learning approach for Boolean circuitsin terms of area/delay/test-error trade-off.
AU  - Boroumand,S
AU  - Bouganis,C
AU  - Constantinides,G
DO  - 10.1145/3394885.3431559
EP  - 529
PB  - ACM
PY  - 2021///
SP  - 524
TI  - Learning Boolean circuits from examples for approximate logic synthesis
UR  - http://dx.doi.org/10.1145/3394885.3431559
UR  - http://hdl.handle.net/10044/1/83482
ER  -

Download

ProfessorChristos-SavvasBouganis

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)