The limitations of deep learning
Mon 17 July 2017
By Francois Chollet
This post is adapted from Section 2 of Chapter 9 of my book, Deep Learning with Python (Manning Publications). It is part of a series of two posts on the current limitations of deep learning, and its future.
This post is targeted at people who already have significant experience with deep learning (e.g. people who have read chapters 1 through 8 of the book). We assume a lot of pre-existing knowledge.
Deep learning: the geometric view
The most surprising thing about deep learning is how simple it is. Ten years ago, no one expected that we would achieve such amazing results on machine perception problems by using simple parametric models trained with gradient descent. Now, it turns out that all you need is sufficiently large parametric models trained with gradient descent on sufficiently many examples. As Feynman once said about the universe, “It’s not complicated, it’s just a lot of it”.