SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

NeurIPS 2017 Kristof T. SchüttPieter-Jan KindermansHuziel E. SaucedaStefan ChmielaAlexandre TkatchenkoKlaus-Robert Müller

Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be the first choice for images, audio and video data, the atoms in molecules are not restricted to a grid... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Formation Energy QM9 SchNet MAE 0.31 # 1