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:20211208T164413Z
LOCATION:Level 2 - Lobby
DTSTART;TZID=America/Los_Angeles:20211208T180000
DTEND;TZID=America/Los_Angeles:20211208T190000
UID:dac_DAC 2021_sess243_WIP178@linklings.com
SUMMARY:CANCELLED: RoHNAS–When Robustness Meets HW-Aware NAS: A Neur
 al Architecture Search Framework with Conjoint Optimization for Adversaria
 l Robustness and Hardware Efficiency of Convolutional and Capsule Networks
DESCRIPTION:Networking Reception, Work-in-Progress Poster\n\nCANCELLED: Ro
 HNAS–When Robustness Meets HW-Aware NAS: A Neural Architecture Searc
 h Framework with Conjoint Optimization for Adversarial Robustness and Hard
 ware Efficiency of Convolutional and Capsule Networks\n\nMrazek\n\nNeural 
 Architecture Search (NAS) algorithms aim at finding high accurate Deep Neu
 ral Network (DNN) architectures for a given application. However, DNNs are
  computationally-complex as well as vulnerable to adversarial attacks. Tow
 ards this, we propose RoHNAS, a novel NAS framework that jointly optimizes
  for the adversarial-robustness and hardware-efficiency of DNNs executed o
 n specialized hardware accelerators. RoHNAS additionally accounts for comp
 lex types of DNNs such as Capsule Networks. RoHNAS analyzes and selects va
 lues of adversarial perturbation for each dataset to employ in the NAS. Ou
 r evaluations provide a set of Pareto-optimal solutions, leveraging the tr
 adeoff between the above-discussed design objectives.\n\nVirtual Program: 
 Presented In-Person
END:VEVENT
END:VCALENDAR