BYU

Abstract by Kennedy Lincoln

Personal Infomation


Presenter's Name

Kennedy Lincoln

Co-Presenters

None

Degree Level

Undergraduate

Co-Authors

Chandramoul Nyshadham

Abstract Infomation


Department

Physics and Astronomy

Faculty Advisor

Gus Hart

Title

Representations in Machine Learning

Abstract

Currently, computationally finding new materials with high accuracy is expensive and time-consuming. Machine learning can help us reduce the cost of calculations to a great extent.  For machine learning methods to be effective, we need a unique representation of crystal structures. Describing the atomic systems require a representation that is invariant to translations, rotations, and permutations of the crystal structure. In this talk, we will present the importance of representations in machine learning with a simple example.