Timezone: »

 
Poster
SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
Kristof Schütt · Pieter-Jan Kindermans · Huziel Enoc Sauceda Felix · Stefan Chmiela · Alexandre Tkatchenko · Klaus-Robert Müller

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #79
in Posters Mon »

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. Instead, their precise locations contain essential physical information, that would get lost if discretized. Thus, we propose to use continuous-filter convolutional layers to be able to model local correlations without requiring the data to lie on a grid. We apply those layers in SchNet: a novel deep learning architecture modeling quantum interactions in molecules. We obtain a joint model for the total energy and interatomic forces that follows fundamental quantum-chemical principles. Our architecture achieves state-of-the-art performance for benchmarks of equilibrium molecules and molecular dynamics trajectories. Finally, we introduce a more challenging benchmark with chemical and structural variations that suggests the path for further work.

Keywords: Deep Learning · Supervised Deep Networks · Applications
[ Code]  [ Paper] 

Author Information

Kristof Schütt (TU Berlin)
Pieter-Jan Kindermans (Google Brain)
Huziel Enoc Sauceda Felix (Fritz-Haber-Institut der Max-Planck-Gesellschaft)
Stefan Chmiela (Technische Universität Berlin)
Alexandre Tkatchenko (University of Luxembourg)
Klaus-Robert Müller (TU Berlin)

More from the Same Authors