Learning representations of molecules and materials with atomistic neural networks
This work addresses the challenge of efficient representation learning for molecules and materials in chemistry and materials science, but it appears incremental as it builds on existing deep learning methods for structured data.
The authors tackled the problem of predicting chemical properties of molecules and materials by developing neural network architectures, specifically SchNet, which accurately predicts properties across datasets with evidence that the learned representations align with chemical intuition.
Deep Learning has been shown to learn efficient representations for structured data such as image, text or audio. In this chapter, we present neural network architectures that are able to learn efficient representations of molecules and materials. In particular, the continuous-filter convolutional network SchNet accurately predicts chemical properties across compositional and configurational space on a variety of datasets. Beyond that, we analyze the obtained representations to find evidence that their spatial and chemical properties agree with chemical intuition.