The joint E-MRS/MRS tutorial on “{Deep, Reinforcement, Active} Learning for Materials Science & Competition” aims to introduce scientists and engineers from the field of materials science to novel computer-based planning and execution of experiments, as well as data analysis approaches, in order to support the research and development of new materials and processes. It is believed that AI-based working techniques will significantly change the way that research and development will be carried out in the future. The aim of the tutorial is to acquaint the participants with state-of-the-art methods applied in AI-based research and development. This tutorial will conclude with an interactive competition in which participants can run their own active learning campaign.

Learning objectives:

• High-level understanding of data science as it relates to materials research
• Experience using Python for machine learning using Google Colab
• Understanding of the principles of active learning, deep learning, and reinforcement learning
• Experience running an active learning campaign including image processing with deep learning.

Introduction to Machine Learning and Materials Data Science 
A. Gilad Kusne, National Institute of Standards and Technology

A high-level introduction to the basic concepts of Machine Learning and central challenges in applying these concepts to materials data.

Introduction to Gaussian Processes for Regression and Classification 
A. Gilad Kusne, National Institute of Standards and Technology

A high level-introduction to the basics of Gaussian Processes (GP), their applications to regression and classification tasks, and their relationship to deep learning and linear regression. We will also have a brief hands-on demonstration of GPs applied to materials data. For attendees interested in following along, please bring a laptop and have a Google account.

A Gentle Introduction to Deep Learning 
Stefan Sandfeld, Forschungszentrum Jülich GmbH

A brief introduction to artificial neural networks (Neural Network Definition and Elements, Custom layers, Activation Functions, Loss functions) as well as to Deep Neural Networks (CNN, RNN) will be given. This is complemented by examples that focus on materials science applications, such as semantic segmentation of images.

Sequential Bayesian Experimental Design 
Kris Reyes, University of Buffalo

This module will cover sequential experimental design and the Bayesian modeling of experimental responses. Key to this is the idea of a decision-making policy. We will provide examples of such policies for various design tasks. Topics discussed will include Gaussian Processes, Multi-armed Bandits and Bayesian Optimization.

Active Learning Competition
Shijing Sun, Toyota Research Center

A hands-on demonstration of active learning in action. This includes a competition where attendees will compete in using Bayesian Optimization to identify the global extrema of a hidden function. Attendees who would like to participate in the competition should bring a laptop and have a Google account. Prizes will be awarded.