BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20230312T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231105T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230404T183715Z
UID:7C25CC77-229F-47CD-8C51-9AA6A9099DC0
DTSTART;TZID=America/Chicago:20230330T120000
DTEND;TZID=America/Chicago:20230330T130000
DESCRIPTION:Thanks to electronic enabling technologies\, machine learning (
 ML) has gained momentum to get a pervasive paradigm in many applications d
 ue to the unquestionable results achieved. Yet\, ML appears as a misused b
 uzzword for attracting scientific interest and curiosity. The main problem
  of ML is the vastity of the tools and techniques mostly linked to neural 
 network architec-tures. In this presentation\, I will show how a niche of 
 ML\, based on statistical inference\, could achieve highly reliable predic
 tive models on reduced da-tasets. Instead of increasing the architectures 
 to follow the algorithmic com-plexity\, I will show a reverse approach\, w
 here the simplicity of the predictive models could be embedded in simple\,
  low-power architectures. The main ad-vantages of these techniques are fir
 st to avoid complex elaborations\, being suitable for edge computing\, and
  secondly to develop tools on a robust mathe-matical background\, such as 
 multivariate analysis helping the developers to a critical understanding o
 f the raw data. I will show results on different appli-cations based on sp
 ectral sensing information processing in precision agricul-ture and struct
 ural engineering and how this approach could be extended to any kind of sp
 ectral sensing (microwave\, mm-wave\, terahertz radiation\, ultra-sound\, 
 optical\, infra-red\, mass spectroscopy).\n\nSpeaker(s): Marco Tartagni\, 
 \n\nVirtual: https://events.vtools.ieee.org/m/352167
LOCATION:Virtual: https://events.vtools.ieee.org/m/352167
ORGANIZER:sfpietri@gmail.com
SEQUENCE:3
SUMMARY:Feed Your Mind - Highly-Efficient Machine Learning Without Neural N
 etworks
URL;VALUE=URI:https://events.vtools.ieee.org/m/352167
X-ALT-DESC:Description: <br /><p>Thanks to electronic enabling technologies
 \, machine learning (ML) has gained momentum to get a pervasive paradigm i
 n many applications due to the unquestionable results achieved. Yet\, ML a
 ppears as a misused buzzword for attracting scientific interest and curios
 ity. The main problem of ML is the vastity of the tools and techniques mos
 tly linked to neural network architec-tures. In this presentation\, I will
  show how a niche of ML\, based on statistical inference\, could achieve h
 ighly reliable predictive models on reduced da-tasets. Instead of increasi
 ng the architectures to follow the algorithmic com-plexity\, I will show a
  reverse approach\, where the simplicity of the predictive models could be
  embedded in simple\, low-power architectures. The main ad-vantages of the
 se techniques are first to avoid complex elaborations\, being suitable for
  edge computing\, and secondly to develop tools on a robust mathe-matical 
 background\, such as multivariate analysis helping the developers to a cri
 tical understanding of the raw data. I will show results on different appl
 i-cations based on spectral sensing information processing in precision ag
 ricul-ture and structural engineering and how this approach could be exten
 ded to any kind of spectral sensing (microwave\, mm-wave\, terahertz radia
 tion\, ultra-sound\, optical\, infra-red\, mass spectroscopy).</p>
END:VEVENT
END:VCALENDAR