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:20251102T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250523T005523Z
UID:46BA6D26-B81E-4584-8917-32C5E9C9D4CE
DTSTART;TZID=America/New_York:20250521T190000
DTEND;TZID=America/New_York:20250521T210000
DESCRIPTION:[] []\n\nThe [IEEE Long Island (LI) Chapter Communications Soci
 ety](https://ieee.li/society-chapters/communications-society-comsoc/) in c
 o-sponsor collaboration with[IEEE LI Chapter Signal Processing Society (SP
 S)](https://ieee.li/society-chapters/signal-processing-society-sp/) presen
 ts the following Distinguished Lecture:\n\nAbstract:\n\nGenerative Adversa
 rial Networks (GANs) implement Machine Learning (ML) algorithms that have 
 the ability to address competitive resource allocation problems together w
 ith detection and mitigation of anomalous behavior. In this talk\, we disc
 uss their use in next-generation (NextG) communications within the context
  of cognitive networks to address i) spectrum sharing\, ii) detecting anom
 alies\, and iii) mitigating security attacks. GANs have the following adva
 ntages. First\, they can learn and synthesize field data\, which can be co
 stly\, time consuming\, and nonrepeatable. Second\, they enable pre-traini
 ng classifiers by using semi supervised data. Third\, they facilitate incr
 eased resolution. Fourth\, they enable recovering corrupted bits in the sp
 ectrum. The talk will provide basics of GANs\, a comparative discussion on
  different kinds of GANs\, performance measures for GANs in computer visio
 n and image processing as well as wireless applications\, a number of data
 sets for wireless applications\, performance measures for general classifi
 ers\, a survey of the literature on GANs for i)–iii) above\, some simula
 tion results\, and future research directions. In the spectrum sharing pro
 blem\, connections to cognitive wireless networks are established. Simulat
 ion results show that a particular GAN implementation is better than a con
 volutional autoencoder for an outlier detection problem in spectrum sensin
 g.\n\nSpeaker(s): Dr. Ender Ayanoglu\, \n\nVirtual: https://events.vtools.
 ieee.org/m/472695
LOCATION:Virtual: https://events.vtools.ieee.org/m/472695
ORGANIZER:eeprof@hotmail.com
SEQUENCE:32
SUMMARY:Machine Learning in NextG Networks via Generative Adversarial Netwo
 rks
URL;VALUE=URI:https://events.vtools.ieee.org/m/472695
X-ALT-DESC:Description: <br /><p class="MsoNormal">&nbsp\; &nbsp\; &nbsp\; 
 &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &n
 bsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; <img src="https://events.vtools.ieee
 .org/vtools_ui/media/display/fb75f7ed-6585-410c-a2b0-a9ac558c53a0" alt="" 
 width="300" height="150"> &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; <img src
 ="https://events.vtools.ieee.org/vtools_ui/media/display/1a5afb01-7e15-4a1
 3-a50f-fff724807ffe" alt="" width="329" height="220"></p>\n<p class="MsoNo
 rmal">&nbsp\;</p>\n<p class="MsoNormal">The&nbsp\;<a href="https://ieee.li
 /society-chapters/communications-society-comsoc/">IEEE Long Island (LI) Ch
 apter Communications Society</a> in co-sponsor collaboration with<a href="
 https://ieee.li/society-chapters/signal-processing-society-sp/"> IEEE LI C
 hapter Signal Processing Society (SPS)</a> presents the following Distingu
 ished Lecture:</p>\n<p class="MsoNormal">Abstract:</p>\n<p class="MsoNorma
 l">Generative Adversarial Networks (GANs) implement Machine Learning (ML) 
 algorithms that have the ability to address competitive resource allocatio
 n problems together with detection and mitigation of anomalous behavior. I
 n this talk\, we discuss their use in next-generation (NextG) communicatio
 ns within the context of cognitive networks to address i) spectrum sharing
 \, ii) detecting anomalies\, and iii) mitigating security attacks. GANs ha
 ve the following advantages. First\, they can learn and synthesize field d
 ata\, which can be costly\, time consuming\, and nonrepeatable. Second\, t
 hey enable pre-training classifiers by using semi supervised data. Third\,
  they facilitate increased resolution. Fourth\, they enable recovering cor
 rupted bits in the spectrum. The talk will provide basics of GANs\, a comp
 arative discussion on different kinds of GANs\, performance measures for G
 ANs in computer vision and image processing as well as wireless applicatio
 ns\, a number of datasets for wireless applications\, performance measures
  for general classifiers\, a survey of the literature on GANs for i)&ndash
 \;iii) above\, some simulation results\, and future research directions. I
 n the spectrum sharing problem\, connections to cognitive wireless network
 s are established. Simulation results show that a particular GAN implement
 ation is better than a convolutional autoencoder for an outlier detection 
 problem in spectrum sensing.</p>
END:VEVENT
END:VCALENDAR