BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Mountain BEGIN:DAYLIGHT DTSTART:20220313T030000 TZOFFSETFROM:-0700 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:MDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20211107T010000 TZOFFSETFROM:-0600 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:MST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20220211T025934Z UID:408E969D-1C42-48A9-9B2A-726430955357 DTSTART;TZID=US/Mountain:20220210T180000 DTEND;TZID=US/Mountain:20220210T190000 DESCRIPTION:The millimeter-wave (mm-Wave) massive MIMO communications emplo y hybrid analog-digital beamforming architectures to reduce the cost-power -size-hardware overheads. Lately\, there is also a gradual push to move fr om the millimeter-wave (mmWave) to Terahertz (THz) frequencies for short-r ange communications and radar applications to exploit very wide THz bandwi dths. The design of the hybrid beamforming techniques requires solving dif ficult nonconvex optimization problems that involve a common performance m etric as a cost function and a number of constraints related to the employ ed communications/radar regime and the adopted architecture of the hybrid systems. There is no standard methodology for solving such problems and us ually\, the derivation of an efficient solution is a very challenging task . Since optimization-based approaches suffer from high computational compl exity and their performance strongly relies on the perfect channel conditi on\, we introduce deep learning (DL) techniques that provide robust perfor mance while designing a hybrid beamformer. These methods offer advantages such as low computational complexity and the ability to extrapolate new fe atures from a limited set of features contained in a training set. In this talk\, the audience will learn about applying DL to various aspects of hy brid beamforming including channel estimation\, antenna selection\, wideba nd beamforming\, knowledge transfer across various geometries\, and spatia l modulation in both communications and radar.\n\nCo-sponsored by: Owen He rman\, Lanbing Shan\, Eugene Freeman\, Mark Milliman\n\nSpeaker(s): Kumar Vijay Mishra\, \n\n2155 East Wesley Avenue\, Denver\, Colorado\, United St ates\, 80208\, Virtual: https://events.vtools.ieee.org/m/294435 LOCATION:2155 East Wesley Avenue\, Denver\, Colorado\, United States\, 8020 8\, Virtual: https://events.vtools.ieee.org/m/294435 ORGANIZER:gowansj@computer.org SEQUENCE:7 SUMMARY:IEEE CIR: Deep learning Techniques for Hybrid Beamforming in Commun ications and Radar URL;VALUE=URI:https://events.vtools.ieee.org/m/294435 X-ALT-DESC:Description: <br /><p>The millimeter-wave (mm-Wave) massive MIMO communications employ hybrid analog-digital beamforming architectures to reduce the cost-power-size-hardware overheads. Lately\, there is also a gr adual push to move from the millimeter-wave (mmWave) to Terahertz (THz) fr equencies for short-range communications and radar applications to exploit very wide THz bandwidths. The design of the hybrid beamforming techniques requires solving difficult nonconvex optimization problems that involve a common performance metric as a cost function and a number of constraints related to the employed communications/radar regime and the adopted archit ecture of the hybrid systems. There is no standard methodology for solving such problems and usually\, the derivation of an efficient solution is a very challenging task. Since optimization-based approaches suffer from hig h computational complexity and their performance strongly relies on the pe rfect channel condition\, we introduce deep learning (DL) techniques that provide robust performance while designing a hybrid beamformer. These meth ods offer advantages such as low computational complexity and the ability to extrapolate new features from a limited set of features contained in a training set. In this talk\, the audience will learn about applying DL to various aspects of hybrid beamforming including channel estimation\, anten na selection\, wideband beamforming\, knowledge transfer across various ge ometries\, and spatial modulation in both communications and radar.</p> END:VEVENT END:VCALENDAR