Clarifying trust of materials property predictions using neural networks with distribution-specific uncertainty quantification

It is critical that machine learning (ML) model predictions be trustworthy for high-throughput catalyst discovery approaches. Uncertainty quantification (UQ) methods allow estimation of the trustworthiness of an ML model, but these methods have not been well explored in the field of heterogeneous ca...

Full description

Bibliographic Details
Main Authors:	Goldsmith, B.R (Author), Gruich, C.J (Author), Madhavan, V. (Author), Wang, Y. (Author)
Format:	Article
Language:	English
Published:	Institute of Physics 2023
Subjects:	]+ catalyst calibration Calibration Catalysis Catalysts Computational catalyse computational catalysis Convolution Convolutional neural network Convolutional neural networks Crystal graph convolutional neural network crystal graph convolutional neural networks Crystal graphs evidential regression Evidential regression Forecasting Monte Carlo methods Neural-networks Quantification methods recalibration Recalibrations Regression analysis Uncertainty analysis Uncertainty quantifications
Online Access:	View Fulltext in Publisher View in Scopus

Internet

View Fulltext in Publisher
View in Scopus

Clarifying trust of materials property predictions using neural networks with distribution-specific uncertainty quantification

Internet

Similar Items