BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2022//speaker//8DGYCX
BEGIN:VEVENT
UID:pretalx-juliacon-2022-Z7MXFS@pretalx.com
DTSTART:20220728T165000Z
DTEND:20220728T170000Z
DESCRIPTION:Treating deep neural networks probabilistically comes with nume
 rous advantages including improved robustness and greater interpretability
 . These factors are key to building artificial intelligence (AI) that is t
 rustworthy. A drawback commonly associated with existing Bayesian methods 
 is that they increase computational costs. Recent work has shown that Baye
 sian deep learning can be effortless through Laplace approximation. This t
 alk presents an implementation in Julia: `BayesLaplace.jl`.
DTSTAMP:20260509T140433Z
LOCATION:Blue
SUMMARY:Effortless Bayesian Deep Learning through Laplace Redux - Patrick A
 ltmeyer
URL:https://pretalx.com/juliacon-2022/talk/Z7MXFS/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-juliacon-2022-PTFQER@pretalx.com
DTSTART:20220729T131500Z
DTEND:20220729T140000Z
DESCRIPTION:This session hosts all of this year's experience talks.
DTSTAMP:20260509T140433Z
LOCATION:Purple
SUMMARY:Juliacon Experiences - Charlie Kawczynski\, Saranjeet Kaur Bhogal\,
  Patrick Altmeyer\, Olga Eleftherakou\, Arturo Erdely\, Fábio Rodrigues S
 odré\, Martin Smit\, Dr. Vikas Negi\, Jeremiah Lasquety-Reyes\, Garrek St
 emo\, Marina Cagliari\, Valeria Perez\, Agustin Covarrubias\, Julia Frank
URL:https://pretalx.com/juliacon-2022/talk/PTFQER/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-juliacon-2022-HU8FVH@pretalx.com
DTSTART:20220729T170000Z
DTEND:20220729T173000Z
DESCRIPTION:We propose [`CounterfactualExplanations.jl`](https://www.paltme
 yer.com/CounterfactualExplanations.jl/dev/): a package for explaining blac
 k-box models through counterfactuals. Counterfactual explanations are base
 d on the simple idea of strategically perturbing model inputs to change mo
 del predictions. Our package is novel\, easy-to-use and extensible. It can
  be used to explain custom predictive models including those developed and
  trained in other programming languages.
DTSTAMP:20260509T140433Z
LOCATION:Red
SUMMARY:Explaining Black-Box Models through Counterfactuals - Patrick Altme
 yer
URL:https://pretalx.com/juliacon-2022/talk/HU8FVH/
END:VEVENT
END:VCALENDAR