David Pfau (@pfau) on X

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.

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

,

at DeepMind and Matthew Foulkes at Imperial. Now I know *almost* nothing about quantum chemistry.