BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Canada/Newfoundland
BEGIN:DAYLIGHT
DTSTART:20220313T030000
TZOFFSETFROM:-0430
TZOFFSETTO:-0330
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:NDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20211107T010000
TZOFFSETFROM:-0330
TZOFFSETTO:-0430
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:NST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20220106T140057Z
UID:3D8A3757-CFE8-4065-9CAA-B332182C51D2
DTSTART;TZID=Canada/Newfoundland:20211126T093000
DTEND;TZID=Canada/Newfoundland:20211126T103000
DESCRIPTION:This technical presentation will discuss the applications of ma
 chine learning techniques to address the challenges of analog electronic d
 esign automation (EDA) and Micro-Electro-Mechanical Systems (MEMS) design 
 automation. Upon the basics of the reinforcement learning technique\, we w
 ill talk about our recent studies in the areas of analog integrated circui
 t (IC) sizing and analog layout placement. We will also discuss our deep-l
 earning-based optimization for designing a low-frequency piezoelectric MEM
 S energy harvester. Some research insights on machine learning in analog E
 DA and MEMS design automation will be presented at the end of the talk.\n\
 nSpeaker(s): Dr. Lihong Zhang\, \n\nSt. John's\, Newfoundland and Labrador
 \, Canada\, Virtual: https://events.vtools.ieee.org/m/290276
LOCATION:St. John's\, Newfoundland and Labrador\, Canada\, Virtual: https:/
 /events.vtools.ieee.org/m/290276
ORGANIZER:lzhang@mun.ca
SEQUENCE:4
SUMMARY:Machine Learning Applications to IC and MEMS Design Automation
URL;VALUE=URI:https://events.vtools.ieee.org/m/290276
X-ALT-DESC:Description: <br /><p>This technical presentation will discuss t
 he applications of machine learning techniques to address the challenges o
 f analog electronic design automation (EDA) and Micro-Electro-Mechanical S
 ystems (MEMS) design automation. Upon the basics of the reinforcement lear
 ning technique\, we will talk about our recent studies in the areas of ana
 log integrated circuit (IC) sizing and analog layout placement. We will al
 so discuss our deep-learning-based optimization for designing a low-freque
 ncy piezoelectric MEMS energy harvester. Some research insights on machine
  learning in analog EDA and MEMS design automation will be presented at th
 e end of the talk.</p>
END:VEVENT
END:VCALENDAR