BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-cz-2025//speaker//YCM9QN
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-devconf-cz-2025-377BND@pretalx.devconf.info
DTSTART;TZID=CET:20250614T123000
DTEND;TZID=CET:20250614T130500
DESCRIPTION:Traditional user interfaces rely on users explicitly setting pr
 eferences to personalize their experience. However\, on-device machine lea
 rning (ML) offers the potential to create adaptive UIs that dynamically ad
 just in real-time based on user behavior\, reducing the need for manual co
 nfiguration.\n\nThis talk explores the feasibility of deploying ML models 
 directly on the client-side\, focusing on performance trade-offs\, resourc
 e constraints\, and user experience considerations. We will examine the ch
 allenges and benefits of running ML models in browsers or edge devices\, d
 iscussing whether this approach can lead to smarter\, more responsive UIs 
 without compromising performance.\n\n**Key Discussion Points**:\n\n1. The 
 Limitations of Explicit User Preferences\n      - How current UI personali
 zation relies on manual user input \n      - Challenges in creating truly 
 seamless adaptive experiences\n\n2. On-Device ML for Implicit UI Adaptatio
 n\n      - Feasibility of embedding ML models within the frontend\n      -
  Practical use cases: behavioral analysis\, theme adaptation\, interaction
  prediction \n        \n3. Performance & Technical Feasibility\n      - Be
 nchmarking ML models in browsers (TensorFlow.js\, ONNX.js\, WebAssembly)\n
       - Computational trade-offs: latency\, memory usage\, battery impact\
 n\n4. User Experience & Ethical Considerations\n      - Does adaptive UI e
 nhance or frustrate users?\n      - Privacy benefits vs. security risks of
  on-device ML
DTSTAMP:20260908T054635Z
LOCATION:D0207 (capacity 90)
SUMMARY:The Feasibility of On-Device Machine Learning for Adaptive User Int
 erfaces in Frontend Development - Sahil Budhwar
URL:https://pretalx.devconf.info/devconf-cz-2025/talk/377BND/
END:VEVENT
END:VCALENDAR