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:20211207T055400Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20211118T083000
DTEND;TZID=America/Chicago:20211118T170000
UID:submissions.supercomputing.org_SC21_sess243_spostg115@linklings.com
SUMMARY:Embeddings Are All You Need: Transfer Learning in Convolutional Ne
 ural Networks Using Word Embeddings
DESCRIPTION:ACM Student Research Competition: Graduate Poster, ACM Student
  Research Competition: Undergraduate Poster, Posters\n\nEmbeddings Are All
  You Need: Transfer Learning in Convolutional Neural Networks Using Word E
 mbeddings\n\nBaughman\n\nRecent advances in efficient neural networks and 
 relational learning using word embeddings as prediction targets for image 
 classification indicate the combination of these two  concepts offers prom
 ise for efficient transfer learning. Given the properties of word embeddin
 gs to represent information-dense abstractions of language concepts in arb
 itrary vector spaces, the projection of an image into that same vector spa
 ce has been shown to enable similar relational operations between images t
 hat are possible with word embeddings. In this essay, we describe how we e
 xtend this idea to show how training a neural network model under this reg
 ime can lead to transfer learning within the embeddings' vector space. Thi
 s allows the model an advantage in predicting classes of images not previo
 usly encountered. Additionally, we demonstrate this principle using a neur
 al network architecture previously shown to be state-of-the-art for model 
 efficiency, demonstrating the applications of these methods in light weigh
 t machine learning.\n\nTag: In-Person Only\n\nRegistration Category: Tech 
 Program Reg Pass, Exhibit Hall Only
END:VEVENT
END:VCALENDAR