back

by brandonb·9y ago·view on hn ↗
This seems like a sincere comment, so in case it's helpful, here's my interpretation of why others may be downvoting it.

Deep learning practitioners are aware that they're using non-convex optimization, stochastic gradient descent, and so on. In fact, those topics are core to modern deep learning research and explicitly acknowledged in most published research: LSTMs were invented to solve the vanishing gradient problem, Restricted Boltzmann Machines were used as a pre-training step to avoid local minima, and optimizers like ADAM have explicit guarantees about things like convergence.

You may know all this stuff already--not sure, based on your comment above.

If not, here are a few example papers from mainstream AI researchers explicitly talking about deep learning as an optimization problem or function approximator: [1] Why Does Unsupervised Pre-training Help Deep Learning?http://www.jmlr.org/papers/volume11/erhan10a/erhan10a.pdf [2] Multilayer feedforward networks are universal approximators: http://www.sciencedirect.com/science/article/pii/08936080899... [3] Deep Learning, Nature. http://www.cs.toronto.edu/~hinton/absps/NatureDeepReview.pdf [4] Adam: A Method for Stochastic Optimization. https://arxiv.org/abs/1412.6980

2 comments
I believe it's a version of an old copypasta [0].

[0] https://wiki.installgentoo.com/index.php/Interjection

Well, I guess my sincerity detector is officially broken, huh?
> Deep learning practitioners are aware that they're using non-convex optimization

It really depends. It's now perfectly possible to use deep learning as a black box, and I've already seen many people use it that way.

Just like you don't have to know how a web-browser works to be a web-programmer, you don't have to know how deep learning works to (e.g.) train a classifier.