Dear Colleagues,

nanoHUB is excited to announce the first four workshops for the Spring 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 participnts

will be able to incorporate in their work. Hands-on activities will use nanoHUB cloud computing resources, no need to download or install any software. All you 

need is an internet connection and a browser. After the training sessions, you will be able to continue using nanoHUB for research or education.

Registration links and material for prior workshops can be found at the workshop webpage: https://nanohub.org/groups/ml/handsontraining

Register soon as seats are limited.  

Date/Time: January 13, 2021 / 1 PM – 2 PM EST

Title: Unsupervised clustering methods for image segmentation: application to scanning electron microscopy images of graphene
By: Aagam Shah, Darren Adams, Sameh Tawfick, and Elif Ertekin 
Register here (limited seats): https://purdue.webex.com/purdue/onstage/g.php?MTID=e59389ef6d05f46ccf735e8d734e14bfa
Abstract: In digital image processing and computer vision, image segmentation refers to the process of partitioning a digital image into multiple segments or related sets of pixels.  This tutorial introduces you to U-Net, a popular convolutional neural network commonly developed for image segmentation in biomedicine. Using an assembled data set, you will learn how to create and train a U-Net neural network, and apply it to segment scanning electron microscopy images of graphene on a substrate. 

Date/Time: January 20, 2021 / 1 PM – 2 PM EST

Title: U-Net convolutional neural networks for image segmentation: application to scanning electron microscopy images of graphene
By: Aagam Shah, Darren Adams, Sameh Tawfick, and Elif Ertekin 
Register here (limited seats): https://purdue.webex.com/purdue/onstage/g.php?MTID=e1891210e556e375681ad9cbd6c6f3d2f
Abstract:  In digital image processing and computer vision, image segmentation refers to the process of partitioning a digital image into multiple segments or related sets of pixels.  This tutorial introduces you to U-Net, a popular convolutional neural network commonly developed for image segmentation in biomedicine. Using an assembled data set, you will learn how to create and train a U-Net neural network, and apply it to segment scanning electron microscopy images of graphene on a substrate. 

Date/Time: January 27, 2021 / 1 PM – 2 PM EST

Title: Constructing Accurate Quantitative Structure-Property Relationships via Materials Graph Networks
By: Yunxing Zuo, Chi Chen, and Shyue Ping Ong
Register here (limited seats): https://purdue.webex.com/purdue/onstage/g.php?MTID=e43ba4d6399d343e2cde9aa0c8afad53f
Abstract: This tutorial covers materials graph networks for modeling crystal and molecular properties. We will introduce the graph representation of crystals and molecules and how the convolutional operations are carried out on the materials graphs. Then we will introduce the megnet package for constructing the graph network models, setting up the model for training and the model evaluation. We will show examples of graph models using computational data from the Materials Project database.

Date/Time: February 3, 2021 / 1 PM – 2 PM EST

Title: Convenient and efficient evelopment of Machine Learning Interatomic Potentials
By: Chi Chen, Yunxing Zuo, and Shyue Ping Ong

Register here (limited seats): https://purdue.webex.com/purdue/onstage/g.php?MTID=e135394b9269645c5f55a869ad51a909e
Abstract: This tutorial introduces the concepts of machine learning interatomic potentials (ML-IAPs) in materials science, including two components of local environment atomic descriptors and machine learning models. Using the prepared dataset, you will learn how to build a prototype ML-IAP and use it to predict basic material properties for a multi-component system.

We hope that you can attend this workshop and walk away with enough information and practical skills to kickstart your foray into deep learning methods for your research or classroom use.

Best regards,

Prof. Ale Strachan, Materials Engineering, Purdue University
Deputy Director, nanoHUB. http://nanohub.org/

--

Alejandro Strachan

Professor of Materials Engineering, Purdue University

Network for Computational Nanotechnology - nanohub.org

Center for Predictive Materials and Devices (c-PRIMED)