,
6 tweets,
2 min read
Read on Twitter
Thrilled to be able to share what I've been working on for the last year - solving the fundamental equations of quantum mechanics with deep learning!
arxiv.org/abs/1909.02487
arxiv.org/abs/1909.02487
The Schroedinger equation - basically Newton's laws at the atomic scale - have been known for almost 100 years. But the equations are impossible to solve in closed form for anything more complicated than a hydrogen atom.
To quote Paul Dirac, "Physical laws necessary for the mathematical theory of a large part of physics and the whole of chemistry are thus completely known, and the difficulty is only that the exact application of these laws leads to equations much too complicated to be soluble."
People have been solving these equations computationally almost as long as there have been computers - but an incredibly high level of accuracy is needed for these computations to be relevant to chemistry - something like 99.999% accuracy or higher.
We've developed a new neural network architecture that can represent wavefunctions for systems of fermions - the kind of particles that make up most matter - and show that it is much more accurate than conventional approximate wavefunctions.
I should say, I knew nothing about quantum chemistry before I started this project, and I'm incredibly grateful to my collaborators @exp_n, @alexggmatthews at DeepMind and Matthew Foulkes at Imperial. Now I know *almost* nothing about quantum chemistry.
