BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2022//speaker//NXZATT
BEGIN:VEVENT
SUMMARY:Bender.jl: A utility package for customizable deep learning - Rasm
 us Kjær Høier
DTSTART:20220728T164000Z
DTEND:20220728T165000Z
DTSTAMP:20260817T075354Z
UID:pretalx-juliacon-2022-7S9YZV@pretalx.com
DESCRIPTION:A wide range of research on feedforward neural networks requir
 es "bending" the chain rule during backpropagation. The package Bender.jl 
 provides neural network layers (compatible with Flux.jl)\, which gives use
 rs more freedom to choose every aspect of the forward mapping. This makes 
 it easy to leverage ChainRules.jl to compose a wide range of experiments\,
  such as training binary neural networks\, Feedback Alignment and Direct F
 eedback Alignment in just a few lines of code.
LOCATION:Blue
URL:https://pretalx.com/juliacon-2022/talk/7S9YZV/
END:VEVENT
END:VCALENDAR