Accelerated electronic structure with deep learning

Our group (CLEAN@NRC) seeks a postdoctoral fellow for a project linking deep neural networks with electronic structure theory. So far, we have shown that deep networks can be used to solve the Schrodinger Equation (https://journals.aps.org/pra/abstract/10.1103/PhysRevA.96.042113), classical spin models (https://doi.org/10.1103/PhysRevE.97.032119), and 2d-materials such as graphene and boron-nitride (https://doi.org/10.1016/j.commatsci.2018.03.005).

The project will explore the use of our recently reported extensive deep neural networks (https://arxiv.org/abs/1708.06686) to the electronic structure problem within the density functional theory. The objective is to show that EDNN can outperform "traditional" electronic structure methods by a factor of 1,000,000. We will generate predictive results 1000 times faster than is currently possible and work on problems 1000 times larger than can currently be modelled.

Salary = $65,000 CAD / year for two years + relocation allowance + conference travel allowance

Location = Ottawa, Ontario, Canada

Coffee = free

Apply here

Applicants should provide a CV, Statement of Interest, and contact information for 3 references

Application deadline = 10 May 2018

Ad URL: http://clean.energyscience.ca/positions/pdf