BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Stakeholder needs to AI Factory use cases: SLAIF user stories for 
 heritable cancer early detection (DISARM–PREDI‑LYNCH–SHIELD)
DTSTART:20260522T070000Z
DTEND:20260522T130000Z
DTSTAMP:20260514T031200Z
UID:indico-event-3812@indico.ijs.si
CONTACT:events@slaif.si
DESCRIPTION:Speakers: Zala Meklav\, Izidor Mlakar\n\nCourse provider: Uni
 versity of Maribor\, Faculty of Electrical Engineering and Computer Scienc
 e (UM FERI)Instructors: Izidor Mlakar (UM FERI)\, Zala Meklav (UM FERI)\nL
 earning objectives: Gain practical knowledge on what FMs exist and where 
 they are useful.\nCourse content: The course will overview the main method
 ological ideas on how to build\, adapt\, and evaluate large self-supervise
 d models for biosignals (e.g.\, PPG\, ECG\, EEG …) and motion sensors (a
 ccelerometers\, gyroscopes) under the messy constraints of real-world wear
 ables (noise\, motion artifacts\, missingness\, device/site shifts\, and l
 imited labels). The training covers modern foundation-model backbones for
  time series (CNN and ResNet encoders\, Transformers\, etc.)\, pretraining
  paradigms (masked modeling\, contrastive/relative contrastive learning)\,
  and representation design choices that matter specifically for physiology
  (beat-synchronous views\, morphology-aware learning). Moreover we will hi
 ghlight state-of-the-art approaches on merging LLMs and sensor-based model
 s that result in hybrid approaches allowing for human-language interpretat
 ion of wearable data (e.g.\, SensorLM).\nLearning outcomes: Practical know
 ledge on what FMs exist\, where they are useful\, and how to take them bey
 ond default setups to be useful in their domains and problems.\n\nhttps://
 indico.ijs.si/event/3812/
IMAGE;VALUE=URI:https://indico.ijs.si/event/3812/logo-1596601024.png
LOCATION:Pompeii
URL:https://indico.ijs.si/event/3812/
END:VEVENT
END:VCALENDAR