http://colah.github.io/posts/201509NNTypesFP/

#1 KirinDave:
Folks who are into this may also like the "Type Safe Neural Networks in Haskell" https://blog.jle.im/entry/practicaldependenttypesinhaske...
I'm also starting work on a set of bindings to libdarknet for Idris with similar properties.

#2 partycoder:
Note that the article has a comment by Yann LeCun (hopefully it's not an impersonator).
You may also be interested in Differentiable Neural Computers:
 https://deepmind.com/blog/differentiableneuralcomputers/

#3 dang:
Discussed at the time: item?id=10165716.

#4 charlescearl:
Some related work also include:
 "StronglyTyped Recurrent Neural Networks" http://proceedings.mlr.press/v48/balduzzi16.pdf
 Principled Approaches to Deep Learning workshop http://padl.ws/ (maybe this is in line with the metapoint Colah's paper)
 Haskell accelerate library https://github.com/AccelerateHS/accelerate/. Not deep learning per se but perhaps some of the ideas are applicable

#5 gtani:
This covers some of same topics plus the rapidly expanding #s of frameworks, SIMD /SIMT backends etc https://julialang.org/blog/2017/12/ml&pl
20 pg tutorial on why RNN's are tricky https://arxiv.org/abs/1801.01078

#6 josquindesprez:
There's also this take on differentiating datatypes: https://codewords.recurse.com/issues/three/algebraandcalcu...
Reading this makes a lot of the operations in colah's article feel more intuitive. (To me, at least. I'm no expert here.)

#7 platz:
The examples are odd because he doesn't incorporate any notion of differentiability.
So a Generating RNN is not quite like foldr, since foldr has no notion of differentiability.
One needs to show examples that pulls in some kind of automaticdifferentiation capability.