Overview

Instructor(s): Jian Tao and Levi McClenny

Time: Friday, March 26, 2021 — 1:30PM-4:00PM CT

Location: Zoom session only

Prerequisite(s): Julia, basic understanding of partial differential equations and numerical methods.

Scientific Machine Learning (SciML) is an emerging area that brings together the fields of Machine Learning and Scientific Computation. SciML introduces scientific model constraints in Machine Learning algorithms, allowing prediction of future performance of complex multiscale, multiphysics systems using sparse, low-fidelity, and heterogeneous data. Unlike traditional black-box Machine Learning methods, SciML aims to deliver interpretable models, leading to improved verification and validation in mission-critical applications.

This short course will introduce the basics of scientific machine learning based on Julia libraries.

Course Materials

Materials

This short course will introduce the basics of scientific machine learning based on Julia libraries.

• Julia Programming Language Link
• SciML Projects Link
• Scientific Machine Learning (Spring 2021): PDF

Agenda

This course focuses, among others, on the following topics:

• Brief introduction to scientific machine learning (SciML) methods
• Open source SciML software packages in Julia
• Introduction to the NeuralPDE.jl package, which utilizes deep neural networks and neural stochastic differential equations to solve partial differential equations,
• Hands-on exercises

This short course will make use of the Jupyter interactive environment.