BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Brussels BEGIN:DAYLIGHT DTSTART:20260329T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20261025T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260921T091813Z UID:C82DDFC0-3D00-4933-9971-9EA903A3FCF6 DTSTART;TZID=Europe/Brussels:20260918T140000 DTEND;TZID=Europe/Brussels:20260918T150000 DESCRIPTION:The rapid evolution of wireless technologies continues to drive the demand for increasingly advanced antenna solutions. Simultaneously\, breakthroughs in artificial intelligence (AI)\, particularly in generative neural network methods\, are opening new frontiers in antenna design.\n\n This talk begins with a brief overview of the challenges involved in high- performance antenna design\, emphasizing the need to explore broader desig n spaces to increase degrees of freedom and uncover novel solutions. To ad dress the resulting complexity\, transformative deep learning (DL) models\ , a subset of machine learning (ML) within AI\, are introduced as tools fo r generative synthesis in antenna design.\n\nThree design exemplars utiliz ing generative adversarial networks (GANs) are presented\, demonstrating i nnovative approaches to metacell design within metasurfaces. These are ach ieved through pixelization strategies and DL-driven algorithms. A particul ar focus is placed on integrating prior knowledge (PK) into the DL-based s ynthesis process\, illustrating its effectiveness in generating metacells for metalens applications.\n\nThe presentation further highlights how meta lenses synthesized using PK-guided DL methods exhibit breakthrough perform ance and offer enhanced functionalities in metalens antenna design. The ta lk concludes with a forward-looking perspective on the integration of AI a nd antenna engineering\, outlining its transformative potential and the em erging challenges and opportunities in this evolving interdisciplinary dom ain.\n\nSpeaker(s): Professor Zhi Ning Chen\, \n\nRoom: IDLab9\, Bldg: 126 \, Technologiepark Zwijnaarde \, Gent\, Oost-Vlaanderen\, Belgium\, 9052 LOCATION:Room: IDLab9\, Bldg: 126\, Technologiepark Zwijnaarde \, Gent\, Oo st-Vlaanderen\, Belgium\, 9052 ORGANIZER:KamilYavuz.Kapusuz@imec.be SEQUENCE:24 SUMMARY:AntennAI: Towards Prior-knowledge Guided Machine-learning Enabled G enerative Antenna Design URL;VALUE=URI:https://events.vtools.ieee.org/m/574220 X-ALT-DESC:Description: <br /><p><span data-olk-copy-source="MessageBody">T he rapid evolution of wireless technologies continues to drive the demand for increasingly advanced antenna solutions. Simultaneously\, breakthrough s in artificial intelligence (AI)\, particularly in generative neural netw ork methods\, are opening new frontiers in antenna design.</span></p>\n<p> This talk begins with a brief overview of the challenges involved in high- performance antenna design\, emphasizing the need to explore broader desig n spaces to increase degrees of freedom and uncover novel solutions. To ad dress the resulting complexity\, transformative deep learning (DL) models\ , a subset of machine learning (ML) within AI\, are introduced as tools fo r generative synthesis in antenna design.</p>\n<p>Three design exemplars u tilizing generative adversarial networks (GANs) are presented\, demonstrat ing innovative approaches to metacell design within metasurfaces. These ar e achieved through pixelization strategies and DL-driven algorithms. A par ticular focus is placed on integrating prior knowledge (PK) into the DL-ba sed synthesis process\, illustrating its effectiveness in generating metac ells for metalens applications.</p>\n<p>The presentation further highlight s how metalenses synthesized using PK-guided DL methods exhibit breakthrou gh performance and offer enhanced functionalities in metalens antenna desi gn. The talk concludes with a forward-looking perspective on the integrati on of AI and antenna engineering\, outlining its transformative potential and the emerging challenges and opportunities in this evolving interdiscip linary domain.</p> END:VEVENT END:VCALENDAR