University of Cambridge > > Theoretical Physics Colloquium > The Problem with Deep Learning in Science (and how to fix it).

The Problem with Deep Learning in Science (and how to fix it).

Add to your list(s) Download to your calendar using vCal

  • UserMiles Cranmer, DAMTP
  • ClockWednesday 08 November 2023, 14:00-15:00
  • HouseMR2.

If you have a question about this talk, please contact Amanda Stagg.

Would Kepler have discovered his laws if machine learning had been around in 1609? Or would he have been satisfied with the accuracy of some black box regression model, leaving Newton without the inspiration to find the law of gravitation? In this talk I will present a quick introduction to machine learning and two major issues facing its application in the sciences: (1) a lack of interpretability, and (2) no physical priors. I will then present new potential solutions to each of these. For (1), I will introduce a method for translating a neural network into a symbolic model, using symbolic regression techniques such as PySR ( Then, for (2), I will discuss the idea behind “foundation models,” which are large, general models pre-trained on vast amounts of data, endowing them with strong general priors – such as ChatGPT and Stable Diffusion. I will present “Polymathic AI,” a new research collaboration ( which aims to build an analogous foundation model for scientific data, and describe our recent work.

This talk is part of the Theoretical Physics Colloquium series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity