Deep Learning and Mathematical Intuition: A Review of (Davies et al. 2021)

by   Ernest Davis, et al.

A recent paper by Davies et al (2021) describes how deep learning (DL) technology was used to find plausible hypotheses that have led to two original mathematical results: one in knot theory, one in representation theory. I argue here that the significance and novelty of this application of DL technology to mathematics is significantly overstated in the paper under review and has been wildly overstated in some of the accounts in the popular science press. In the knot theory result, the role of DL was small, and a conventional statistical analysis would probably have sufficed. In the representation theory result, the role of DL is much larger; however, it is not very different in kind from what has been done in experimental mathematics for decades. Moreover, it is not clear whether the distinctive features of DL that make it useful here will apply across a wide range of mathematical problems. Finally, I argue that the DL here "guides human intuition" is unhelpful and misleading; what the DL does primarily does is to mark many possible conjectures as false and a few others as possibly worthy of study. Certainly the representation theory result represents an original and interesting application of DL to mathematical research, but its larger significance is uncertain.


page 1

page 2

page 3

page 4


Comment on "Open is not forever: a study of vanished open access journals"

We comment on a recent article by Laakso et al. (arXiv:2008.11933 [cs.DL...

Transgressing the boundaries: towards a rigorous understanding of deep learning and its (non-)robustness

The recent advances in machine learning in various fields of application...

Can the Language of the Collation be Translated into the Language of the Stemma? Using Machine Translation for Witness Localization

Stemmatology is a subfield of philology where one approach to understand...

A Statistician Teaches Deep Learning

Deep learning (DL) has gained much attention and become increasingly pop...

Model-Constrained Deep Learning Approaches for Inverse Problems

Deep Learning (DL), in particular deep neural networks (DNN), by design ...

Fiducial Inference and Decision Theory

The majority of the statisticians concluded many decades ago that fiduci...

Mathematics of Deep Learning

Recently there has been a dramatic increase in the performance of recogn...

Please sign up or login with your details

Forgot password? Click here to reset