Neural Networks in Python

Bethany Lusch, ALCF
Austin Clyde, Argonne National Laboratory

Trainees will learn the basics of neural networks, opening up the black box of machine learning by building out by-hand networks for linear regression to increase the understanding of the math that goes into machine learning methods.

Designing Therapeutics with AI and HPC - Therapeutic design is changing rapidly. Starting in 2018 with the insight that molecules can be embedded in continuous vector-representations with neural networks, drug design has rapidly bene moving towards a tight integration with HPC and AI. Argonne's Austin Clyde will speak briefly about some of the conceptual steps to move from thinking about the science problems to translating them into exascale-ready inverse-design workflows through outlining my own process in designing the National Virtual Biotechnology Laboratory’s drug design workflow during the COVID-19 Pandemic. 

About the Speakers

Bethany Lusch is an Assistant Computer Scientist in the data science group at the Argonne Leadership Computing Facility at Argonne National Lab. Her research expertise includes developing methods and tools to integrate AI with science, especially for dynamical systems and PDE-based simulations. Her recent work includes developing machine-learning emulators to replace expensive parts of simulations, such as computational fluid dynamics simulations of engines and climate simulations. She is also working on methods that incorporate domain knowledge in machine learning, representation learning, and using machine learning to analyze supercomputer logs. She holds a Ph.D. and MS in applied mathematics from the University of Washington and a BS in mathematics from the University of Notre Dame.

Austin Clyde is an assistant computational scientist in the Data Science and Learning Division at Argonne National Laboratory. Previously, he was a visiting research fellow Harvard Kennedy School’s Program on Science, Technology, and Society. His research in drug discovery focuses on applying exascale computing and artificial intelligence to design small-molecule inhibitors which was a major component of his work with the National Virtual Biotechnology Laboratory.