High-dimensional Bayesian optimization of 23 hyperparameters over 100 iterations for an attention-based network to predict materials property: A case study on …

SG Baird, M Liu, TD Sparks - Computational Materials Science, 2022 - Elsevier
Expensive-to-train deep learning models can benefit from an optimization of the
hyperparameters that determine the model architecture. We optimize 23 hyperparameters of …

DiSCoVeR: a materials discovery screening tool for high performance, unique chemical compositions

SG Baird, TQ Diep, TD Sparks - Digital Discovery, 2022 - pubs.rsc.org
We present Descending from Stochastic Clustering Variance Regression
(DiSCoVeR)(https://www. github. com/sparks-baird/mat_discover), a Python tool for …

High-dimensional bayesian optimization of hyperparameters for an attention-based network to predict materials property: a case study on CrabNet using Ax and …

SG Baird, M Liu, TD Sparks - arxiv preprint arxiv:2203.12597, 2022 - arxiv.org
Expensive-to-train deep learning models can benefit from an optimization of the
hyperparameters that determine the model architecture. We optimize 23 hyperparameters of …

WyckoffTransformer: Generation of Symmetric Crystals

N Kazeev, R Zhu, I Romanov, AE Ustyuzhanin… - AI for Accelerated … - openreview.net
We propose WyckoffTransformer, a generative model for inorganic materials that takes
advantage of the high order symmetry present in most known crystals. Wyckoff positions, a …