Predicting Properties of Crystals

Lapchevskyi, Kostiantyn

Home
→
Students Research & Project Works | Роботи студентів
→
Факультет прикладних наук
→
Освітня програма наук про дані
→
2020
→
View Item

dc.contributor.author	Lapchevskyi, Kostiantyn
dc.date.accessioned	2020-06-17T23:45:44Z
dc.date.available	2020-06-17T23:45:44Z
dc.date.issued	2020
dc.identifier.citation	Lapchevskyi, Kostiantyn. Predicting Properties of Crystals : Master Thesis : manuscript rights / Kostiantyn Lapchevskyi ; Supervisor Dr. Tess Eleonora Smidt ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2020. – 59 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/2242
dc.language.iso	en	uk
dc.subject	predicting	uk
dc.subject	EuclideanNeural Networks	uk
dc.subject	crystalline structures	uk
dc.title	Predicting Properties of Crystals	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	Crystalline structures are vital to the modern technology. Yet, we are still only starting to ﬁgure out how to properly estimate their directional properties using machine learning techniques. In order to improvethat, I build uponthe theory and codebase of Euclidean Neural Networks (networks equivariant to 3D rotations). The main contributions of this work are: a derivation of the decompositon/reconstruction equations of elastic tensor that enables using it as a train target, optimized CUDA implementation of the core operation PeriodicConvolution that makes it fast and scalable, and ananalys is of the trends of geometric structures and electronic properties of the crystal in Materials Project Database and how these trends impact hyper-parameters for convolutional neural network architectures such as Euclidean Neural Networks.	uk