If you are interested in attending a workshop, please select them when you register for the conference.
There is no additional fee for workshops.
Introduction to Machine Learning Approach for Materials Discovery
Michael Shatruk (FSU) and Anton Oliynyk (University of Houston)
DetailsInteractive Quantum Chemistry: an Introduction to the Open-Source Psi Program
Eugene DePrince (FSU), Lori Burns (Georgia Tech), Ryan Fortenberry (Georgia Southern), and David Sherrill (Georgia Tech)
Details“What to do next?”
Exploring career options from academia to industry
- Connector.
Organizers
TBD
- Connector.
Audience
Students (undergraduate and graduate welcome) and postdocs
- Connector.
Where and When
Thursday May 4th, 1-5PM
- Connector.
Details
To be announced
Introduction to Machine Learning Approach for Materials Discovery
- Connector.
Organizers
Michael Shatruk (FSU) and Anton Oliynyk (University of Houston)
- Connector.
Audience
Graduate students, postdocs, and faculty
- Connector.
Where and When
Thursday May 4th, 1-5PM
- Connector.
Details
Historically, the approach in searching for new materials involved systematic construction of phase diagrams or serendipitous discovery. The problem is that the chemical whitespace is too vast to be explored in such an incremental manner. A new paradigm is needed. The Materials Genome Initiative (MGI) initiated in 2011 calls “to discover, develop, and deploy new materials twice as fast.” The idea is to analyze “large data” to accelerate the development of new materials. By processing the wealth of freely accessible scientific data available in the literature, scientists can elucidate complex structure-property relationships to improve the design of new materials and molecules. The key step is to guide this analysis by machine learning algorithms. Successful application of machine learning approaches in materials chemistry includes discovery of unexpected new class of thermoelectric materials, screening for materials with superior mechanical properties, and prediction of crystal structures for compounds with simple stoichiometries.
This workshop will provide an overview of machine learning methods with a specific focus on large collection of chemical data. The introduction to the practical application will include data processing and preparation aspects, as well as creating and running machine-learning models on free demo version software. Participants will have an opportunity to learn step-by-step how to handle the data, use the models, and interpret the results. No prior programming experience is required to participate in the workshop.
Interactive Quantum Chemistry: a Psi4 Users Workshop
- Connector.
Organizers
Eugene DePrince (FSU), Lori Burns (Georgia Tech), Ryan Fortenberry (Georgia Southern), and David Sherrill (Georgia Tech)
- Connector.
Audience
Graduate students, postdocs, and faculty
- Connector.
Where and When
Thursday May 4th, 1-5PM
- Connector.
Details
Quantum-chemical computations are an increasingly important component of modern chemical research. Psi4 is a freely-available, open-source program providing many popular electronic structure methods, including those based upon density functional theory, many-body perturbation theory, coupled-cluster theory, and configuration interaction. It has been designed to be as user-friendly as possible, both for beginning computational chemists and for advanced users. For users who want to automate complex workflows, Psi4 can now be called from a Python script as a regular Python module. This workshop will introduce the Psi4 program and how it can be used in research or education. A series of freely-available computational chemistry lab modules, available through the Psi4Education project, will also be introduced.