BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2026//speaker//EMBAGL
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-juliacon-2026-HBY8MD@pretalx.com
DTSTART;TZID=CET:20260813T150000
DTEND;TZID=CET:20260813T153000
DESCRIPTION:[CounterfactualTraining.jl](https://github.com/JuliaTrustworthy
 AI/CounterfactualTraining.jl) leverages [CounterfactualExplanations.jl](ht
 tps://github.com/JuliaTrustworthyAI/CounterfactualExplanations.jl) to make
  opaque machine learning models like artificial neural networks more 1) ex
 plainable\, 2) sensitive to actionability constraints and 3) adversarially
  robust. The package is part of the [Taija](https://www.taija.org/) ecosys
 tem for Trustworthy AI in Julia and the engine behind our [IEEE SaTML 2026
 ](https://satml.org/accepted-papers/) paper titled *[Counterfactual Traini
 ng: Teaching Models Plausible and Actionable Explanations](https://arxiv.o
 rg/abs/2601.16205)*.
DTSTAMP:20260529T230824Z
LOCATION:Room 6
SUMMARY:Teaching Opaque Machine Learning Models Plausible and Actionable Ex
 planations - Patrick Altmeyer
URL:https://pretalx.com/juliacon-2026/talk/HBY8MD/
END:VEVENT
END:VCALENDAR