BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260124T045345Z UID:FD5731B1-96AE-429A-A070-7435E6E0C18B DTSTART;TZID=America/Los_Angeles:20250812T180000 DTEND;TZID=America/Los_Angeles:20250812T191500 DESCRIPTION:Generative Adversarial Networks (GANs) implement Machine Learni ng (ML) algorithms that can address competitive resource allocation proble ms\, together with detection and mitigation of anomalous behavior. In this talk\, the speaker will discuss their use in next-generation (NextG) comm unications within the context of cognitive networks to address i) spectrum sharing\, ii) detecting anomalies\, and iii) mitigating security attacks. GANs have the following advantages. First\, they can learn and synthesize field data\, which can be costly\, time-consuming\, and non-repeatable. S econd\, they enable pre-training classifiers by using semisupervised data. Third\, they facilitate increased resolution. Fourth\, they enable recove ring corrupted bits in the spectrum. The talk will provide basics of GANs\ , a comparative discussion on different kinds of GANs\, performance measur es for GANs in computer vision and image processing as well as wireless ap plications\, a number of datasets for wireless applications\, performance measures for general classifiers\, a survey of the literature on GANs for i)–iii) above\, some simulation results\, and future research directions . In the spectrum sharing problem\, connections to cognitive wireless netw orks are established. Simulation results show that a particular GAN implem entation is better than a convolutional autoencoder for an outlier detecti on problem in spectrum sensing.\n\nCo-sponsored by: Vishnu S. Pendyala\, S JSU\n\nSpeaker(s): Dr. Vishnu S. Pendyala\, Prof. Ender Ayanoglu\n\nVirtua l: https://events.vtools.ieee.org/m/493301 LOCATION:Virtual: https://events.vtools.ieee.org/m/493301 ORGANIZER:pendyala@ieee.org SEQUENCE:83 SUMMARY:Distinguished Lecture: Machine Learning in NextG Networks via Gener ative Adversarial Networks URL;VALUE=URI:https://events.vtools.ieee.org/m/493301 X-ALT-DESC:Description: <br /><p>Generative Adversarial Networks (GANs) imp lement Machine Learning (ML)&nbsp\;algorithms that can address competitive resource allocation problems\, together with detection and mitigation of& nbsp\;anomalous behavior. In this talk\, the speaker will discuss their us e in next-generation (NextG) communications within the context of cognitiv e&nbsp\;networks to address i) spectrum sharing\, ii) detecting anomalies\ , and&nbsp\;iii) mitigating security attacks. GANs have the following&nbsp \;advantages. First\, they can learn and synthesize field data\, which can &nbsp\;be costly\, time-consuming\, and non-repeatable. Second\, they enab le&nbsp\;pre-training classifiers by using semisupervised data. Third\, th ey&nbsp\;facilitate increased resolution. Fourth\, they enable recovering& nbsp\;corrupted bits in the spectrum. The talk will provide basics of GANs \,&nbsp\;a comparative discussion on different kinds of GANs\, performance &nbsp\;measures for GANs in computer vision and image processing as well a s&nbsp\;wireless applications\, a number of datasets for wireless applicat ions\,&nbsp\;performance measures for general classifiers\, a survey of th e&nbsp\;literature on GANs for i)&ndash\;iii) above\, some simulation resu lts\, and&nbsp\;future research directions. In the spectrum sharing proble m\,&nbsp\;connections to cognitive wireless networks are established. Simu lation&nbsp\;results show that a particular GAN implementation is better t han a&nbsp\;convolutional autoencoder for an outlier detection problem in spectrum&nbsp\;sensing.</p> END:VEVENT END:VCALENDAR