"Why deep learning works?

Matthieu Wyart | Professor of Theoretical Physics in the School of Basic Sciences at EPFL.

“General arguments suggest that classifying data in large dimension (for example a picture can live in 100 pixels *100 pixels=10000 dimensions, compared to us who live in 3 Should be impossible: the number of data to train on to achieve good performance should be larger than the number atoms in the universe. Yet, it works: with 1000 000 data you can learn to recognise cats from dogs. It means that pictures are not generic: they have a lot of symmetry and structure in them, that we do not know yet how to describe mathematically. We would like to build a theory that can understand the number of necessary data to learn a rule. Currently we do not even know what fixes its order of magnitude: for cats and dogs, why isn’t it one hundred, or instead one billion billions? “

I am attaching a paper we are writing on this topic, maybe the intro is readable for a non-specialist:
[Link]

︎︎︎ Matthieu Wyart Publications

HEADQUARTER

????

ABOUT

SUBMISSION

(Post to be screened there) (Scroll down to access older entries)(Layout TBD)

(Post to be screened there)
(Scroll down to access older entries)
(Layout TBD)