[maxwells-daemon]

Yes, the way I see it, one of the major benefits of deep learning is that it lets you define functions (in the R^n -> R^m sense) that would be basically impossible to define with traditional programming techniques. I think this comes up a lot in subroutines of combinatorial optimization, like heuristics for guiding search on subsets of NP-complete problems. The fact that you can automatically evaluate the heuristic and train by RL is also very convenient.