Hynes, Level 2, Room 210
RECENTLY UPDATED! Machine Learning (ML) and Artificial Intelligence (AI) are powerful techniques that materials scientists can use to help analyze their data, choose experiments and discover new materials.
Instructors: Austin McDannald, National Institute of Standards and Technology
Machine Learning (ML) and Artificial Intelligence (AI) are powerful techniques that materials scientists can use to help analyze their data and drive autonomous experimentation. This tutorial will start with introducing Gaussian Processes (GPs) as an example ML tool that can work with small data sets. Next, the tutorial will show how GPs can be used to drive autonomous experimentation in a technique known as Active Learning (AL). Lastly, this tutorial will show how GPs and AL can be used to for Autonomous Phase Mapping to discover structure-property relationships. Part of the purpose of this tutorial will be explaining how many of these techniques work, dispelling myths arising from the hype from popular culture. We will also show how these tools can be used for more rigorous material science studies, and how doing so differs from the prototypical ML and AI methods designed by computer science and social for use with largely unstructured data. We show how to adapt the ML and AI methods to the particular data challenges in materials science with the goals of answering scientific inquiries.
After the tutorial, attendees will be familiar with and have the resources to:
8:00 AM
Introduction to Gaussian Processes Austin McDannald; National Institute of Standards and Technology, United States
8:45 AM
Introduction to Active Learning Austin McDannald; National Institute of Standards and Technology, United States
9:30 AM BREAK
10:00 AM
Autonomous Phase Mapping Austin McDannald; National Institute of Standards and Technology, United States
11:00 AM
Open Discussion Austin McDannald; National Institute of Standards and Technology, United States