In Python, libraries like TensorFlow or Theano provide possibility to perform automatic differentiation over their computational graphs. E.g. in TensorFlow (example from SO <http://stackoverflow.com/questions/35226428/how-do-i-get-the-gradient-of-the-loss-at-a-tensorflow-variable> ):
data = tf.placeholder(tf.float32) var = tf.Variable(...) loss = some_function_of(var, data) var_grad = tf.gradients(loss, [var])[0] What is the closest thing in Julia at the moment? Here's what I've checked so far: * ForwardDiff.jl <https://github.com/JuliaDiff/ForwardDiff.jl> - it computes derivatives using forward mode automatic differentiation (AD). Although AD has particular advantages, I found this package quite slow. E.g. for a vector of 1000 elements gradient takes ~100x times longer then the function itself. Another potential issues is that ForwardDiff.jl doesn't output symbolic version of gradient and thus is hardly usable for computation on GPU, for example. * *Calculus.jl* <https://github.com/johnmyleswhite/Calculus.jl> - among other things, this package provided symbolic differentiation. However, it seems to consider all symbols to be numbers and doesn't support matrices or vectors. I have pretty shallow knowledge of both these packages, so please correct me if I'm wrong somewhere in my conclusions. And if not, is there any other package or project that I should consider?