raj0926/mse_fall2023

The materials for the Fall ML in Materials course at the UTK MSE

MSE_Fall2023

Course Announcement for Fall 2023

MACHINE LEARNING FOR MATERIALS: FROM PCA TO CHATGPT

MSE 494/MSE576

Instructor: Sergei V. Kalinin

Times and locations: 10:20 am - 11:10 am MWF, Ferris Hall 502

Join me on a journey into the cutting-edge realm of Machine Learning (ML) in Materials Science, where the possibilities are boundless. ML and Artificial Intelligence (AI) have become the defining features of our era, revolutionizing domains from medicine to autonomous driving. Over the past decade, ML has rapidly advanced, dominating in silico applications such as image analysis, recommender systems, and the development of large language models. Now, envision the forthcoming decade as the era of ML's impact on real-world (you can say “material”) challenges. With ML, we can unlock new frontiers in materials and process optimization, pave the way for groundbreaking materials discovery, and even delve into the intricacies of physics at the nanoscale. This course is designed to equip you with the fundamental knowledge of principles and underpinnings of ML methods while delving deep into the realm of practical applications from lab to the fab. The instructor worked on ML in materials science for 15 years at ORNL and spent a year at Amazon (special projects). By enrolling in this course, you will embark on an exciting exploration of ML's potential in solving real-world scenarios. Discover how ML can revolutionize Materials Science, unraveling complex problems and uncovering innovative solutions. Join today and be at the forefront of this transformative field, where the convergence of ML and Materials Science promises a future brimming with limitless possibilities. Attend if:

1. You are interested in ML and AI and would like to try it hands-on on real world problems from materials science and microscopy to physical characterization
2. Learn the basics of the ML methods and build upon this knowledge - from simple principal component analysis to large language models.
3. Explore how ML is being adopted by industry - from IT leaders such as Amazon, Google, and Meta to instrumental, chemical, and materials companies
4. Learn why next decade of ML will be transition from purely in-silico to real-world materials and device applications, and be a part of this transition
5. Learn to work backwards from real-world problem to solution

If you are an undergraduate student, this course can give you an early edge for adopting ML in the industrial role or graduate school at UTK or elsewhere. If you are a graduate student - welcome to the AI journey in the materials world!

Contact: Sergei V. Kalinin – [email protected]

Course website: https://github.com/SergeiVKalinin/MSE_Fall2023