BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250215T202920Z UID:57237E37-DE27-46E9-970E-E094FF85CAB7 DTSTART;TZID=America/New_York:20250212T140000 DTEND;TZID=America/New_York:20250212T150000 DESCRIPTION:Speaker: Professor Ender Ayanoglu\, University of California\, Irvine\, CA\,\nAbstract: Generative Adversarial Networks (GANs) implement Machine Learning (ML) algorithms that have the ability to address competit ive resource allocation problems together with detection and mitigation of anomalous behavior. In this talk\, we discuss their use in next-generatio n (NextG) communications within the context of cognitive networks to addre ss i) spectrum sharing\, ii) detecting anomalies\, and iii) mitigating sec urity attacks. GANs have the following advantages. First\, they can learn and synthesize field data\, which can be costly\, time consuming\, and non repeatable. Second\, they enable pre-training classifiers by using semi-su pervised data. Third\, they facilitate increased resolution. Fourth\, they enable recovering corrupted bits in the spectrum. The talk will provide b asics of GANs\, a comparative discussion on different kinds of GANs\, perf ormance measures for GANs in computer vision and image processing as well as wireless applications\, a number of datasets for wireless applications\ , performance measures for general classifiers\, a survey of the literatur e on GANs for i)–iii) above\, some simulation results\, and future resea rch directions. In the spectrum sharing problem\, connections to cognitive wireless networks are established. Simulation results show that a particu lar GAN implementation is better than a convolutional autoencoder for an o utlier detection problem in spectrum sensing.\n\nCo-sponsored by: IEEE PCJ S\n\nSpeaker(s): Ender Ayanoglu\, \n\nVirtual: https://events.vtools.ieee. org/m/463498 LOCATION:Virtual: https://events.vtools.ieee.org/m/463498 ORGANIZER:dkinnovate77@gmail.com SEQUENCE:14 SUMMARY:Machine Learning in NextG Networks via Generative Adversarial Netwo rks URL;VALUE=URI:https://events.vtools.ieee.org/m/463498 X-ALT-DESC:Description: <br /><div><strong>Speaker:</strong>&nbsp\;Professo r Ender Ayanoglu\,&nbsp\;University of California\, Irvine\, CA\,</div>\n< div><strong>Abstract: </strong>Generative Adversarial Networks (GANs) impl ement Machine Learning (ML) algorithms that have the ability to address co mpetitive resource allocation problems together with detection and mitigat ion of anomalous behavior. In this talk\, we discuss their use in next-gen eration (NextG) communications within the context of cognitive networks to address i) spectrum sharing\, ii) detecting anomalies\, and iii) mitigati ng security attacks. GANs have the following advantages. First\, they can learn and synthesize field data\, which can be costly\, time consuming\, a nd nonrepeatable. Second\, they enable pre-training classifiers by using s emi-supervised data. Third\, they facilitate increased resolution. Fourth\ , they enable recovering corrupted bits in the spectrum. The talk will pro vide basics of GANs\, a comparative discussion on different kinds of GANs\ , performance measures for GANs in computer vision and image processing as well as wireless applications\, a number of datasets for wireless applica tions\, performance measures for general classifiers\, a survey of the lit erature on GANs for i)&ndash\;iii) above\, some simulation results\, and f uture research directions. In the spectrum sharing problem\, connections t o cognitive wireless networks are established. Simulation results show tha t a particular GAN implementation is better than a convolutional autoencod er for an outlier detection problem in spectrum sensing.</div>\n<div>&nbsp \;</div>\n<div>&nbsp\;</div> END:VEVENT END:VCALENDAR