Yota.jl

Reverse-mode automatic differentiation in Julia
Popularity
145 Stars
Updated Last
10 Months Ago
Started In
July 2018

Yötä

Test

Yota.jl is a package for reverse-mode automatic differentiation in Julia. The main features are:

  • optimized for large inputs and conventional deep learning
  • tracer-based with a hackable computational graph (tape)
  • supports ChainRules API

Used By Packages