EUVIMEDEUVIMED entdecken
Crossref

Towards on-node Machine Learning for Ultra-low-power Sensors Using Asynchronous Σ Δ Streams

Patricia Gonzalez-Guerrero, Tommy Tracy II, Xinfei Guo, Rahul Sreekumar, Marzieh Lenjani, Kevin Skadron, Mircea R. Stan

ACM Journal on Emerging Technologies in Computing Systems · 31.10.2020 · 16 (4) · 1-20

DOI: 10.1145/3404975 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Journal on Emerging Technologies in Computing Systems, online erschienen am 26.08.2020. Verfasst von Patricia Gonzalez-Guerrero und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a novel architecture to enable low-power, complex on-node data processing, for the next generation of sensors for the internet of things (IoT), smartdust, or edge intelligence. Our architecture combines near-analog-memory-computing (NAM) and asynchronous-computing-with-streams (ACS), eliminating the need for ADCs. ACS enables ultra-low power, massive computational resources required to execute on-node complex Machine Learning (ML) algorithms; while NAM addresses the memory-wall that represents a common bottleneck for ML and other complex functions. In ACS an analog value is mapped to an asynchronous stream that can take one of two logic levels ( v h , v l ). This stream-based data representation enables area/power-efficient computing units such as a multiplier implemented as an AND gate yielding savings in power of ∼90% compared to digital approaches. The generation of streams for NAM and ACS in a brute force manner, using analog-to-digital-converters (ADCs) and digital-to-streams-converters, would sky-rocket the power-latency-energy cost making the approach impractical. Our NAM-ACS architecture eliminates expensive conversions, enabling an end-to-end processing on asynchronous streams data-path. We tailor the NAM-ACS architecture for random forest (RaF), an ML algorithm, chosen for its ability to classify using a reduced number of features. Simulations show that our NAM-ACS architecture enables 75% of savings in power compared with a single ADC, obtaining a classification accuracy of 85% using an RaF-inspired algorithm.

Förderung

  • NSF

Zitieren

APA

Gonzalez-Guerrero, P., II, T. T., Guo, X., Sreekumar, R., Lenjani, M., Skadron, K., & Stan, M. R. (2020). Towards on-node Machine Learning for Ultra-low-power Sensors Using Asynchronous Σ Δ Streams. ACM Journal on Emerging Technologies in Computing Systems, 16(4), 1-20. https://doi.org/10.1145/3404975

Vancouver

Gonzalez-Guerrero P, II TT, Guo X, Sreekumar R, Lenjani M, Skadron K, et al. Towards on-node Machine Learning for Ultra-low-power Sensors Using Asynchronous Σ Δ Streams. ACM Journal on Emerging Technologies in Computing Systems. 2020;16(4):1-20. doi:10.1145/3404975

BibTeX
@article{GonzalezGuerrero2020,
  author = {Gonzalez-Guerrero, Patricia and II, Tommy Tracy and Guo, Xinfei and Sreekumar, Rahul and Lenjani, Marzieh and Skadron, Kevin and Stan, Mircea R.},
  title = {Towards on-node Machine Learning for Ultra-low-power Sensors Using Asynchronous Σ Δ Streams},
  journal = {ACM Journal on Emerging Technologies in Computing Systems},
  year = {2020},
  volume = {16},
  number = {4},
  pages = {1--20},
  doi = {10.1145/3404975}
}
Kostenlos starten →