GTC 2020: Accelerating Quantum Chemistry Simulations with AI

GTC 2020 S21273
Presenters: Abe Stern,NVIDIA
Abstract
We’ll discuss computational chemistry applications of machine learning covering three topics. First, we’ll examine the use of neural networks and other machined-learned methods for describing a quantum-accurate potential energy surface. Second, we’ll cover graph convolution neural networks and graph message-passing networks for predicting molecular properties at a fraction of the cost of traditional electronic structure calculations. Third, we’ll discuss variational autoencoders for molecule discovery and illustrate their application to drug discovery.

Watch this session
Join in the conversation below.