Unlocking Efficiency in BNNs: Global by Local Thresholding for Analog-Based HW Accelerators-Reference-Cited by-同舟云学术

Unlocking Efficiency in BNNs: Global by Local Thresholding for Analog-Based HW Accelerators

Published:2023-12 Issue:4 Volume:13 Page:940-955
ISSN:2156-3357
Container-title:IEEE Journal on Emerging and Selected Topics in Circuits and Systems
language:
Short-container-title:IEEE J. Emerg. Sel. Topics Circuits Syst.

Author:

Yayla Mikail¹^ORCID,Frustaci Fabio²^ORCID,Spagnolo Fanny²^ORCID,Chen Jian-Jia¹,Amrouch Hussam³^ORCID

Affiliation:

1. Design Automation for Embedded Systems Group, TU Dortmund University, Dortmund, Germany

2. DIMES Department, University of Calabria, Arcavacata, Italy

3. Chair of AI Processor Design, Technical University of Munich (TUM), Munich, Germany

Funder

Deutsche Forschungsgemeinschaft (DFG) through OneMemory Project

ACCROSS Project

Collaborative Research Center SFB 876 “Providing Information by Resource-Constrained Analysis”

Federal Ministry of Education and Research of Germany and the state of North Rhine-Westphalia as part of the Lamarr-Institute for ML and AI

PON Ricerca Innovazione-MUR through Ministero dell–Universitã e della Ricerca, Italian Government

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering

Link

Reference28 articles.

1. Binarized neural networks;Hubara