BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2022//talk//Z7MXFS
BEGIN:VEVENT
SUMMARY:Effortless Bayesian Deep Learning through Laplace Redux - Patrick 
 Altmeyer
DTSTART:20220728T165000Z
DTEND:20220728T170000Z
DTSTAMP:20260816T124936Z
UID:pretalx-juliacon-2022-Z7MXFS@pretalx.com
DESCRIPTION:Treating deep neural networks probabilistically comes with num
 erous advantages including improved robustness and greater interpretabilit
 y. These factors are key to building artificial intelligence (AI) that is 
 trustworthy. A drawback commonly associated with existing Bayesian methods
  is that they increase computational costs. Recent work has shown that Bay
 esian deep learning can be effortless through Laplace approximation. This 
 talk presents an implementation in Julia: `BayesLaplace.jl`.
LOCATION:Blue
URL:https://pretalx.com/juliacon-2022/talk/Z7MXFS/
END:VEVENT
END:VCALENDAR