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:20241103T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241218T184948Z
UID:BF5D05A9-6AF4-42D0-BA99-7938DBD6E40B
DTSTART;TZID=America/Los_Angeles:20241217T160000
DTEND;TZID=America/Los_Angeles:20241217T180000
DESCRIPTION:Generative Adversarial Networks (GANs) implement Machine Learni
 ng (ML) algorithms that have the ability to address competitive resource a
 llocation problems together with detection and mitigation of anomalous beh
 avior. In this talk\, we 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 semi-supervised data
 . Third\, they facilitate increased resolution. Fourth\, they enable recov
 ering corrupted bits in the spectrum. The talk will provide basics of GANs
 \, a comparative discussion on different kinds of GANs\, performance measu
 res for GANs in computer vision and image processing as well as wireless a
 pplications\, 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 direction
 s. In the spectrum sharing problem\, connections to cognitive wireless net
 works are established. Simulation results show that a particular GAN imple
 mentation is better than a convolutional auto encoder for an outlier detec
 tion problem in spectrum sensing.\n\nSpeaker(s): Ender Ayanoglu\n\nVirtual
 : https://events.vtools.ieee.org/m/446267
LOCATION:Virtual: https://events.vtools.ieee.org/m/446267
ORGANIZER:tromar@cpp.edu
SEQUENCE:67
SUMMARY:Machine Learning in NextG Networks via Generative Adversarial Netwo
 rks
URL;VALUE=URI:https://events.vtools.ieee.org/m/446267
X-ALT-DESC:Description: <br /><p style="text-align: justify\;">Generative A
 dversarial Networks (GANs) implement Machine Learning (ML) algorithms that
  have the ability to address competitive resource allocation problems toge
 ther with detection and mitigation of anomalous behavior. In this talk\, w
 e discuss their use in next-generation (NextG) communications within the c
 ontext of cognitive networks to address i) spectrum sharing\, ii) detectin
 g anomalies\, and iii) mitigating security attacks. GANs have the followin
 g 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-supervised data. Third\, they facilita
 te increased resolution. Fourth\, they enable recovering corrupted bits in
  the spectrum. The talk will provide basics of GANs\, a comparative discus
 sion on different kinds of GANs\, performance measures for GANs in compute
 r vision and image processing as well as wireless applications\, a number 
 of datasets for wireless applications\, performance measures for general c
 lassifiers\, a survey of the literature on GANs for i)&ndash\;iii) above\,
  some simulation results\, and future research directions. In the spectrum
  sharing problem\, connections to cognitive wireless networks are establis
 hed. Simulation results show that a particular GAN implementation is bette
 r than a convolutional auto encoder for an outlier detection problem in sp
 ectrum sensing.</p>
END:VEVENT
END:VCALENDAR