Though it has some constraints, source-rewrite autodiff is appealing when it can apply, because of the potential code efficiency. Especially for reverse-mode autodiff, the most application is to evaluate gradients, which are usually computed lots of times in optimization or sampling algorithms. Rev…

Fate of ReverseDiffSource

cscherrer December 14, 2017, 3:10am 7

Hmm, maybe I could just switch them out? I had looked around for documentation of TypeConstructor and hadn’t had any luck.

Topic		Replies	Views
Using ReverseSourceDiff for a function with matrices New to Julia differentiation	10	848	June 23, 2018
ReverseDiff.jl Community package , announcement	9	1737	December 13, 2017
Automatic Differentiation Machine Learning	11	3338	February 11, 2019
What is the right way to compute Gradient of function of 2 variables with Auto Differentiation? New to Julia package , gradient	6	10194	September 18, 2018
ANN: XDiff.jl - an expression differentiation package Machine Learning	25	4199	August 22, 2017