BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20230312T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20231105T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230411T170017Z UID:104C73BD-E3A3-4F98-AC0E-15CD62BF7720 DTSTART;TZID=America/New_York:20230405T111500 DTEND;TZID=America/New_York:20230405T123000 DESCRIPTION:In recent years\, research in deep learning techniques has attr acted much attention. With the help of big data technology\, massively par allel computing\, and fast optimization algorithms\, deep learning has dra matically improved the performance of many problems in speech and image re search. In electromagnetic engineering\, physical laws provide the theoret ical foundation for research and development. With the development of deep learning\, improving learning capacity may allow machines to “learn” from a large amount of physics data and “master” the physical law in c ertain controlled boundary conditions. In the long run\, combining fundame ntal physical principles with “knowledge” from big data could unleash numerous engineering applications limited by a lack of data information an d computation ability.\n\nIn this short tutorial\, the presenter will shar e some of his learnings in deep learning techniques and discuss the potent ial and feasibility of applying deep learning in computational electromagn etics. The presenter hopes to explore the characteristics\, feasibility\, and challenges of deep learning methods in the field of computational elec tromagnetics through some examples\, such as solving wave equations\, arra y antenna synthesis\, inverse scattering\, etc.\n\nCo-sponsored by: STARaC om Montreal\n\nSpeaker(s): Prof. Maokun Li \, \n\nVirtual: https://events. vtools.ieee.org/m/351680 LOCATION:Virtual: https://events.vtools.ieee.org/m/351680 ORGANIZER:elham.baladi@polymtl.ca SEQUENCE:7 SUMMARY:Application of Deep Learning Techniques in Computational Electromag netics URL;VALUE=URI:https://events.vtools.ieee.org/m/351680 X-ALT-DESC:Description: <br /><p>In recent years\, research in deep learnin g techniques has attracted much attention. With the help of big data techn ology\, massively parallel computing\, and fast optimization algorithms\, deep learning has dramatically improved the performance of many problems i n speech and image research. In electromagnetic engineering\, physical law s provide the theoretical foundation for research and development. With th e development of deep learning\, improving learning capacity may allow mac hines to &ldquo\;learn&rdquo\; from a large amount of physics data and &ld quo\;master&rdquo\; the physical law in certain controlled boundary condit ions. In the long run\, combining fundamental physical principles with &ld quo\;knowledge&rdquo\; from big data could unleash numerous engineering ap plications limited by a lack of data information and computation ability.< /p>\n<p>In this short tutorial\, the presenter will share some of his lear nings in deep learning techniques and discuss the potential and feasibilit y of applying deep learning in computational electromagnetics. The present er hopes to explore the characteristics\, feasibility\, and challenges of deep learning methods in the field of computational electromagnetics throu gh some examples\, such as solving wave equations\, array antenna synthesi s\, inverse scattering\, etc.</p> END:VEVENT END:VCALENDAR