BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2022//speaker//3CFNUV
BEGIN:VEVENT
SUMMARY:Dithering in Julia with DitherPunk.jl - Adrian Hill
DTSTART:20220727T144000Z
DTEND:20220727T145000Z
DTSTAMP:20260820T000550Z
UID:pretalx-juliacon-2022-FXMQPQ@pretalx.com
DESCRIPTION:Dithering algorithms are a group of color quantization techniq
 ues that create the illusion of continuous color in images with small colo
 r palettes by adding high-frequency noise or patterns. Traditionally used 
 in printing\, they are now mostly used for stylistic purposes.\n\nDitherPu
 nk.jl implements a wide variety of fast and extensible dithering algorithm
 s. Using its example\, I will demonstrate how packages for creative coding
  can be built on top of the JuliaImages ecosystem.
LOCATION:Blue
URL:https://pretalx.com/juliacon-2022/talk/FXMQPQ/
END:VEVENT
BEGIN:VEVENT
SUMMARY:ExplainableAI.jl: Interpreting neural networks in Julia - Adrian H
 ill
DTSTART:20220728T172000Z
DTEND:20220728T173000Z
DTSTAMP:20260820T000550Z
UID:pretalx-juliacon-2022-MFU9MN@pretalx.com
DESCRIPTION:In pursuit of interpreting black-box models such as deep image
  classifiers\, a number of techniques have been developed that attribute a
 nd visualize the importance of input features with respect to the output o
 f a model.\nExplainableAI.jl brings several of these methods to Julia\, bu
 ilding on top of primitives from the Flux ecosystem. In this talk\, we wil
 l give an overview of current features and show how the package can easily
  be extended\, allowing users to implement their own methods and rules.
LOCATION:Blue
URL:https://pretalx.com/juliacon-2022/talk/MFU9MN/
END:VEVENT
END:VCALENDAR