From first principles to machine learning methods in materials informatics

Level: advanced

Language: English

Format: online, self-paced

Course duration: 6 hours of lectures/15 hours (0,5 ECTS)

Target audience: This course is designed for researchers, engineers, master and graduate students working in materials engineering, computational materials science, and related fields with a good grasp of atomistic simulations and an interest in learning about machine learning applications in their practice.

Accessibility: Always available for self-study (access to video lectures and other materials on the platform eduportal.kau.org.ua)

Registration.

Accessibility: online lectures + self-study based on video and text materials on the platform eduportal.kau.org.ua, passing the final test;

Lecturer: Oleksandr Vasiliev, Ph.D., Leading Researcher, Associate Professor, Frantsevich Institute for Problems of Materials Science National Academy of Sciences of Ukraine, Head of Department of Applied Mathematics and Computational Experiment in Materials Science, Kyiv Academic University, Department of Applied Physics and Materials Science

Required knowledge:

• intermediate knowledge of machine learning
• good grasp of atomistic modeling of materials with density functional theory
• intermediate Python programming

By the end of this course, participants will be able to:

• understand the specifics of ML models for atomistic simulations
• select the base model for their problem;
• gather and prepare the first-principles data to train the ML models
• understand how to train, validate, and apply the atomistic ML models

You can learn more about the course and the teacher in this video

Skills acquired:

The course is free of charge. After completing the course, all participants who complete the program and pass the test will receive certificates with ECTS credits (0.5 credits).