[dhammack]

There's an interesting python library [1] which implements AD as well as has some neat features like automatic compilation to optimized C. It's developed by the AI lab at the University of Montreal, and is pretty popular in deep learning circles. I've found it to be a huge time saver to not worry whether you screwed up your gradient calculations when doing exploratory research!

[1] http://deeplearning.net/software/theano/

[lightcatcher]

My personal favorite feature of Theano is the automatic compilation to CUDA code (which would get about 8-15x speed-up over the optimized C code for the deep learning research I was doing).