[Bnc-faculty-all-list] FW: nanoHUB Hands-on Machine Learning Workshop

[Black, Nancy Lee]

nanoHUB is excited to announce that a new workshop has been scheduled in the Fall 2021 session of our Hands-on Data Science and Machine Learning Training Series.

Series information: Our series is aimed at active researchers and educators and designed to introduce practical skills with online, hands-on activities that participants will be able to incorporate in their own work. Hands-on activities will use nanoHUB cloud computing resources, negating the need to download or install any software. All that is required of the audience is an internet connection and an hour to spare for the demonstration. After the training sessions, you will be able to continue using nanoHUB for research or education.

Recordings and associated materials from prior workshops can be found at the workshop webpage: https://nanohub.org/groups/ml/handsontraining<https://click.mail.nanohub.org/?qs=cfc1ff07cb30894a21965907d37fc0d278f347b93cec3ead093fc79f56f60ed4f754c574d6b576efff99ab68dcf634a4eb7a921c80f81819>

Register soon as seats are limited.

Date/Time: Wednesday, November 3, 2021 / 1:30 PM - 2:30 PM EDT
Title: Autonomous Neutron Diffraction Experiments with ANDiE
Presenter: Dr. Austin McDannald, National Institute of Standards and Technology

Register for this workshop here<https://click.mail.nanohub.org/?qs=cfc1ff07cb30894ac0eca13582d84c5fe7688847a222720cb682fa8ea4e752c7eecf7b9d544a25e95518aa5db9718d68839997491eaf1a56>

Abstract:  Active learning is a powerful tool that can be used to accelerate experimental research. In this tutorial we will cover how Bayesian Statistics can autonomously guide neutron diffraction measurements, accelerating the research by a factor of 5 compared to traditional methods. Neutron diffraction is one of the only measurement techniques that can directly study the magnetic order in a material. The magnetic transition temperatures and their transition dynamics are important material characteristics for use in many applications including: high-performance electric motors, high-frequency transformers, and solid-state refrigeration. However, determining the magnetic transition characteristics traditionally requires considerable neutron beamtime at already over-subscribed facilities. We developed ANDiE, the autonomous neutron diffraction explorer, that can analyze diffraction measurements on-the-fly and autonomously decide on the best experiment to perform next. This tutorial will cover the working principles of ANDiE, how physics was encoded into the design, and demonstrate how ANDiE can be used to autonomously control neutron diffraction experiments.

Bio: Dr. Austin McDannald received his B.S. in Physics from Worcester Polytechnic Institute in 2010 and his Ph.D in Materials Science and Engineering from the University of Connecticut in 2016. He worked as a Staff Scientist for II-VI M Cubed Technologies Inc. from 2016 to 2020. He joined the National Institute of Standards and Technology in 2020 as a Materials Research Engineer in the Materials Measurement Laboratory. His primary research interests are in encoding materials physics into machine learning and AI tools to enable autonomous experimental materials research.



Regards,

Alejandro Strachan
Deputy Director, nanoHUB


Arun Mannodi Kanakkithodi (he/him/his)
Assistant Professor, School of Materials Engineering, Purdue University
https://www.mannodigroup.com/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: </ECN/mailman/archives/bnc-faculty-all-list/attachments/20211028/6a78cc80/attachment.htm>