Hybridizing physical and data-driven prediction methods for physicochemical properties

Abstract

We present a generic, highly effective approach to combine physical and data-driven prediction methods for physicochemical properties based on Bayesian machine learning and model distillation.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jan 01, 2020
Source ID
10.1039/d0cc05258b

Entities

People

  • Fabian Jirasek
  • Robert Bamler
  • Stephan Mandt

Organizations

  • Defense Advanced Research Projects Agency
  • Department of Computer Science, University of Oxford
  • German Academic Exchange Service
  • National Science Foundation
  • Qualcomm
  • United States Army
  • University of California
  • University of California, Irvine

Tags

Readers

  • Agricultural Chemistry/Soil Science
  • Distributed Systems and Data Platform Development

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks