Tutorial Schedule
8:00 am
Introduction to Machine Learning for Materials Science Arun Mannodi Kanakkithodi, Purdue University
Introduction to ML for materials science, some high-level
examples, discussion of nuts and bolts of ML (data pre- and post-processing, descriptors, similarity measures, methods including linear and random forest regression, packages and tools). Demonstration of training ML models using a dataset of perovskite
band gaps.
9:30 am
Break
10:00 am
Gaussian Process Regression—Detailed Description and Walkthrough of Two ExamplesAustin McDannald, NIST
10:30 am
Discussion of Active Learning, Bayesian Optimization and Autonomous Experiments Through an ExampleAustin McDannald, NIST
11:30 am
General Discussion
12:00 pm
Lunch
1:30 pm
Overview of Neural Networks for Prediction and Convolutional Neural Networks for Image Datasets Saaketh Desai, Sandia National Laboratories
2:30 pm
General Discussion
3:00 pm
Machine Learning Challenge (open until Thursday, December 1) Shijing Sun, Toyota Research Institute
A battery dataset will be assigned to the contestants, who will apply some of the methods discussed during the tutorial and use available scripts to train models and make predictions. Please fill this sign-up form if interested and bring your laptop to the in-person launch at 3:00 pm.