Off-the-shelf deep learning is not enough, and requires parsimony, Bayesianity, and causality

Abstract Deep neural networks (‘deep learning’) have emerged as a technology of choice to tackle problems in speech recognition, computer vision, finance, etc. However, adoption of deep learning in physical domains brings substantial challenges stemming from the correlative nature of deep learning m...

Full description

Bibliographic Details
Main Authors: Rama K. Vasudevan, Maxim Ziatdinov, Lukas Vlcek, Sergei V. Kalinin
Format: Article
Language:English
Published: Nature Portfolio 2021-01-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-020-00487-0