BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//papers.synesthesia.it//ai-heroes-2024//JTCPGB
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-ai-heroes-2024-7H3DK3@papers.synesthesia.it
DTSTART;TZID=CET:20241211T151500
DTEND;TZID=CET:20241211T160000
DESCRIPTION:With the advent of Generative AI\, it has become increasingly c
 ritical to monitor data and models (of any type) in production. This need 
 has led to the development of numerous techniques and tools dedicated to t
 he field of Monitoring and Observability. \nIn this talk\, I will explore 
 the most effective methods for monitoring AI solutions\, covering differen
 t applications that include Large Language Models and classical Machine Le
 arning\, both in batch and streaming contexts.\nI will analyse the common 
 challenges\, such as detecting data drift\, managing anomalies and control
 ling model performance over time. \nFinally\, I will present the open-sour
 ce AI monitoring solution developed by Radicalbit\, a company with extensi
 ve experience in MLOps. This solution not only offers the benefits of cont
 inuous and in-depth model monitoring\, guaranteeing the reliability and ef
 ficiency of AI implementations in production\, but it also fosters a colla
 borative environment in which the community continuously improves the solu
 tion through contributions.
DTSTAMP:20241209T105219Z
LOCATION:Sala 150
SUMMARY:Monitoring AI in Production: Challenges and Open-Source Solutions -
  Mauro Mariniello
URL:https://papers.synesthesia.it/ai-heroes-2024/talk/7H3DK3/
END:VEVENT
END:VCALENDAR