
High Temperature Oxide Property Explorer
29 Jun 2020  Contributor(s):: Zachary D McClure, Alejandro Strachan
Explore material properties of common and niche oxide materials for hightemperature applications

SEM Image Segmentation Tutorial using SEM Image Processing Tool
16 Jun 2020   Contributor(s):: Joshua A Schiller
In this activity, students will learn about the use of image processing methods to analyze Scanning Electron Microscopy images using a technique known as Image Segmentation and the SEM Image Processing Tool. The purpose of this tutorial is demonstrate several methods for image masking:...

Handson Deep Learning for Materials
10 Jun 2020   Contributor(s):: Saaketh Desai, Edward Kim
This tool introduces users to deep learning techniques such as convolutional neural networks and variational auto encoders from a materials standpoint

ECE 595ML: Course Overview
28 May 2020   Contributor(s):: Stanley H. Chan

ECE 595ML Lecture 1.2: Linear Regression  Geometry
28 May 2020   Contributor(s):: Stanley H. Chan

Jon Nykiel
I'm Jon Nykiel, a fourth year undergraduate studying Materials Science and Applied Physics at the Ohio State University. I'm participating in NCN's SCALE URE program with Dr. Strachan of Purdue...
https://nanohub.org/members/288810

Rebecca Mosier
Rebecca Mosier is a secondyear undergraduate student at Johns Hopkins University. Her majors are Biomedical Engineering and Applied Mathematics & Statistics. She is working on the DataDriven...
https://nanohub.org/members/288446

Parsimonious Neural Networks Learn Classical Mechanics and Can Teach It
15 May 2020   Contributor(s):: Saaketh Desai, Alejandro Strachan
We combine neural networks with genetic algorithms to find parsimonious models that describe the time evolution of a point particle subjected to an external potential. The genetic algorithm is designed to find the simplest, most interpretable network compatible with the training data. The...

Handson Unsupervised Learning using Dimensionality Reduction via Matrix Decomposition (2nd offering)
30 Apr 2020   Contributor(s):: Michael N Sakano, Alejandro Strachan
This tutorial introduces unsupervised machine learning algorithms through dimensionality reduction via matrix decomposition techniques in the context of chemical decomposition of reactive materials in a Jupyter notebook on nanoHUB.org. The tool used in this demonstration...

Handson Supervised Learning: Part 2  Classification and Random Forests (2nd offering)
30 Apr 2020   Contributor(s):: Saaketh Desai
This tutorial introduces neural networks for classification tasks and random forests for regression tasks via Jupyter notebooks on nanoHUB.org. You will learn how to create and train a neural network to perform a classification, as well as how to define and train random forests. The tools used...

PennyLane  Automatic Differentiation and Machine Learning of Quantum Computations
29 Apr 2020   Contributor(s):: Nathan Killoran
PennyLane is a Pythonbased software framework for optimization and machine learning of quantum and hybrid quantumclassical computations.

Nathan Killoran
Nathan holds a MSc in Mathematics from the University of Toronto and a PhD in Physics from the University of Waterloo. He specializes in quantum computing, deep learning, and quantum optics.
https://nanohub.org/members/286348

Machine Learning for Chemical Sensing
29 Apr 2020   Contributor(s):: Bruno Ribeiro

Handson Unsupervised Learning using Dimensionality Reduction via Matrix Decomposition (1st offering)
29 Apr 2020   Contributor(s):: Michael N Sakano, Alejandro Strachan
This tutorial introduces unsupervised machine learning algorithms through dimensionality reduction via matrix decomposition techniques in the context of chemical decomposition of reactive materials in a Jupyter notebook on nanoHUB.org. The tool used in this demonstration...

Handson Sequential Learning and Design of Experiments
29 Apr 2020   Contributor(s):: Juan Carlos Verduzco Gastelum, Alejandro Strachan
This tutorial introduces the concept of sequential learning and information acquisition functions and how these algorithms can help reduce the number of experiments required to find an optimal candidate. A handson approach is presented to optimize the ionic conductivity of ceramic...

Image Segmentation for Graphene Images
29 Apr 2020   Contributor(s):: Joshua A Schiller
This lecture outlines the need for a fast, automated means for identifying regions of images corresponding to graphene. Simple methods, like color masking and template matching, are discussed initially. Unsupervised clustering methods are then introduced as potential improvements...

Handson Supervised Learning: Part 2  Classification and Random Forests (1st offering)
24 Apr 2020   Contributor(s):: Saaketh Desai
This tutorial introduces neural networks for classification tasks and random forests for regression tasks via Jupyter notebooks on nanoHUB.org. You will learn how to create and train a neural network to perform a classification, as well as how to define and train random forests. The tools used...

Handson Supervised Learning: Part 1  Linear Regression and Neural Networks
22 Apr 2020   Contributor(s):: Saaketh Desai
This tutorial introduces supervised learning via Jupyter notebooks on nanoHUB.org. You will learn how to setup a basic linear regression in a Jupyter notebook and then create and train a neural network. The tool used in this demonstration is Machine Learning for Materials Science:...

Handson Data Science and Machine Learning Training
21 Apr 2020   Contributor(s):: Alejandro Strachan, Saaketh Desai
This series of handson tutorials is designed to jump start your use of data science and machine learning in research or teaching. This series will cover the following topics:Learn how to use Jupyter notebooks for your researchInteract with data repositories and manage...

Introduction to Jupyter Notebooks, Data Organization and Plotting (1st offering)
21 Apr 2020   Contributor(s):: Juan Carlos Verduzco Gastelum, Alejandro Strachan
This tutorial gives an introductory demonstration of how to create and use Jupyter notebooks. It showcases the libraries Pandas to manipulate and organize data with functionalities similar to those of Excel on python, and Plotly, a library used to create interactive plots for enhanced...