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:20260522T150121Z
LOCATION:D220
DTSTART;TZID=America/Chicago:20181111T142100
DTEND;TZID=America/Chicago:20181111T142400
UID:submissions.supercomputing.org_SC18_sess160_ws_whpc107@linklings.com
SUMMARY:Deep Learning:  Extrapolation Tool for Computational Nuclear Physi
 cs
DESCRIPTION:Gianina Alina Negoita (Iowa State University)\n\nThe goal of n
 uclear theory is to understand how nuclei arise from interacting nucleons 
 based on the underlying theory of the strong interactions, quantum chromod
 ynamics (QCD). The interactions among the nucleons inside a nucleus are do
 minated by the strong interaction, which is non-perturbative in the low-en
 ergy regime relevant for nuclear physics. With access to powerful High Per
 formance Computing (HPC) systems, several ab initio approaches have been d
 eveloped to study nuclear structure and reactions, such as the No-Core She
 ll Model (NCSM). The NCSM  and other approaches require an extrapolation o
 f the results obtained in a finite basis space to the infinite basis space
  limit and assessment of the uncertainty of those extrapolations.  Each ob
 servable requires a separate extrapolation and most observables have no pr
 oven extrapolation method at the present time. We propose a feed-forward a
 rtificial neural network (ANN) method as an extrapolation tool to obtain t
 he ground state energy and the ground state point proton root-mean-square 
 (rms) radius and their extrapolation uncertainties. We have generated theo
 retical data for 6Li by performing ab initio NCSM calculations using basis
  spaces up through the largest computationally feasible basis space. The d
 esigned ANNs are sufficient to produce results for these two very differen
 t observables in ^6Li from the ab initio NCSM results in small basis space
 s that satisfy the following theoretical physics condition: independence o
 f basis space parameters in the limit of extremely large matrices. Compari
 sons of the ANN results with other extrapolation methods are also provided
 .\n\nTag: Diversity, Education, Hot Topics\n\nRegistration Category: Works
 hop Reg Pass\n\nSession Chairs: Toni Collis (Women in High Performance Com
 puting); Weronika Filinger (Edinburgh Parallel Computing Centre (EPCC); Un
 iversity of Edinburgh, Scotland); and Misbah Mubarak (Amazon Web Services)
 \n\n
END:VEVENT
END:VCALENDAR