BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//programme.europython.eu//europython-2023//talk//ZCXMQK
BEGIN:VTIMEZONE
TZID:Europe/Prague
BEGIN:DAYLIGHT
DTSTART:20220720T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221030T030000
RDATE:20231029T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230326T030000
RDATE:20240331T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Understanding Neural Network Architectures with Attention and Diff
 usion - Michał Karzyński
DTSTART;TZID=Europe/Prague:20230720T103000
DTEND;TZID=Europe/Prague:20230720T110000
DTSTAMP:20260904T202326Z
UID:pretalx-europython-2023-ZCXMQK@programme.europython.eu
DESCRIPTION:Neural networks have revolutionized AI\, enabling machines to 
 learn from data and make intelligent decisions. In this talk\, we'll explo
 re two popular architectures: Attention models and Diffusion models.\n\nFi
 rst up\, we'll discuss Attention models and how they've contributed to the
  success of large language models like ChatGPT. We'll explore how the Atte
 ntion mechanism helps GPT focus on specific parts of a text sequence and h
 ow this mechanism has been applied to different tasks in natural language 
 processing.\n\nNext\, we'll dive into Diffusion models\, a class of genera
 tive models that have shown remarkable performance in image synthesis. We'
 ll explain how they work and their potential applications in the creative 
 industry.\n\nThis is a good talk for visual learners. I prepared schematic
  diagrams\, which present main features of the nerual network architecture
 s. By necessity\, the diagrams are oversimplified\, but I believe they wil
 l allow you to gain some insight into Transformers and Latent Diffusion mo
 dels.
LOCATION:South Hall 2B
URL:https://programme.europython.eu/europython-2023/talk/ZCXMQK/
END:VEVENT
END:VCALENDAR