BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Understanding large language models for science and business
DTSTART:20260615T080000Z
DTEND:20260615T120000Z
DTSTAMP:20260612T013900Z
UID:indico-event-3818@indico.ijs.si
CONTACT:events@slaif.si
DESCRIPTION:Speakers: Marko Robnik-Šikonja\n\nCourse provider: University
  of Ljubljana\, Faculty of Computer and Information Science (UL FRI)Instru
 ctors: Marko Robnik-Šikonja (UL FRI)\nLearning objectives: Get acquainted
  with large language models (LLMs)\, their architecture and training\, lea
 ding to their effective use.\nCourse contents: Large language models are c
 hanging the way we write\, read\, and do intellectual jobs. The lecture pr
 esents the working of the transformer architecture of neural networks and 
 focuses on the decoder models\, which are used in generative language mode
 ls\, such as ChatGPT. Explaining their construction\, pretraining\, instru
 ction following\, preference alignment\, and fine-tuning\, the lecture giv
 es the necessary background to understand their behaviour. Based on this\,
  it explains prompting strategies\, such as in-context learning and chain-
 of-thought reasoning. The contents are based on examples from business and
  science.\nLearning outcomes: Knowledge of LLM construction and recommenda
 tions for their use.\n\nhttps://indico.ijs.si/event/3818/
IMAGE;VALUE=URI:https://indico.ijs.si/event/3818/logo-1596601024.png
LOCATION:UL FRI
URL:https://indico.ijs.si/event/3818/
END:VEVENT
END:VCALENDAR