BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T054801Z
LOCATION:230-231-232
DTSTART;TZID=America/Chicago:20211116T160000
DTEND;TZID=America/Chicago:20211116T163000
UID:submissions.supercomputing.org_SC21_sess175_pap118@linklings.com
SUMMARY:Edge-Based Hyperdimensional Learning System with Brain-Like Neural
  Adaptation
DESCRIPTION:Paper\n\nEdge-Based Hyperdimensional Learning System with Brai
 n-Like Neural Adaptation\n\nZou, Kim, Imani, Alimohamadi, Cammarota...\n\n
 Hyperdimensional Computing (HDC) is a brain-inspired learning approach for
  efficient and robust learning on today’s embedded devices. Encoding, or t
 ransforming the input data into high-dimensional representation, is the ke
 y first step of HDC before performing a learning task.  In this paper, we 
 have developed NeuralHD, a new HDC approach with a dynamic encoder for ada
 ptive learning. Inspired by human neural regeneration study in neuroscienc
 e, NeuralHD identifies insignificant dimensions and regenerates those dime
 nsions to enhance the learning capability and robustness. We also present 
 a scalable learning framework to distribute NeuralHD computation over edge
  devices in IoT systems. Our solution enables edge devices capable of real
 -time learning from both labeled and unlabeled data. Our evaluation on a w
 ide range of practical classification tasks shows that NeuralHD provides 5
 .7× and 6.1× (12.3× and 14.1×) faster and more energy-efficient training a
 s compared to the HD-based algorithms (DNNs) running on the same platform.
 \n\nTag: Data Analytics, Machine Learning and Artificial Intelligence\n\nR
 egistration Category: Tech Program Reg Pass
END:VEVENT
END:VCALENDAR