News for hackers. Stuff that matters.
Re:“Deep Learning has outlived its usefulness as a buzz-phrase” by currymj on Friday January 05, 2018 @08:48PM (#16083361)
it seems like it's made by analogy with "probabilistic programming", i.e. defining complex probability distributions by writing familiar-looking imperative code (with loops and whatnot).

I think the idea is that thinking in terms of passing data through layers in a graph is cumbersome sometimes, and that expressing it as a "regular" program that just happens to come with gradients could be more comfortable.

I'd argue that GANs in particular are a natural fit for this style. The training procedure doesn't really fit exactly into the standard "minimize loss function of many layers using backprop".

There are no comments on this comment yet.