BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230712T175214Z
LOCATION:3006\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20230712T155500
DTEND;TZID=America/Los_Angeles:20230712T161000
UID:dac_DAC 2023_sess126_RESEARCH1553@linklings.com
SUMMARY:Cryogenic In-Memory Matrix-Vector Multiplication using Ferroelectr
 ic Superconducting Quantum Interference Device (FE-SQUID)
DESCRIPTION:Research Manuscript\n\nShamiul Alam and Jack Hutchins (Univers
 ity of Tennessee, Knoxville); Md Shafayat Hossain (Princeton University); 
 Kai Ni (Rochester Institute of Technology); Vijaykrishnan Narayanan (Penns
 ylvania State University); and Ahmedullah Aziz (University of Tennessee, K
 noxville)\n\nCryogenic in-memory implementation of machine learning (ML) a
 lgorithms can be a game-changer for quantum computing systems. The Ferroel
 ectric Superconducting Quantum Interference Device (FE-SQUID) is promising
  as a memory element, thanks to its non-volatile nature, voltage-controlle
 d switching, separate read-write paths, and scalability. Here, we demonstr
 ate matrix-vector multiplication (MVM) using FE-SQUID-based cryogenic memo
 ry for energy-efficient implementation of ML algorithms. FE-SQUID-based me
 mory allows optimizing the read operation for in-memory computing without 
 imposing any limits on memory performance. We utilize this FE-SQUID-based 
 in-memory MVM to perform a handwritten digit recognition task and achieve 
 an average accuracy of 95% with the MNIST handwritten digit dataset.\n\nTo
 pic: Design\n\nKeyword: Emerging Device Technologies\n\nSession Chairs: Ka
 i Ni (Rochester Institute of Technology) and Michael Niemier (University o
 f Notre Dame)
END:VEVENT
END:VCALENDAR
