Still time to register to today’s and next week's hands-on machine learning workshop using nanoHUB
Dear Colleagues, A few available seats remain for the first two workshops in the Summer 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. Title: A Hands-on Introduction to Physics-Informed Neural Networks Date: May 26th 2021, 1:30 PM - 2:30 PM EST Speaker: Ilias Bilionis, Purdue University Register here (limited seats): https://nanohub.org/groups/ml/handsontraining Abstract: Can you make a neural network satisfy a physical law? There are two main types of these laws: symmetries and ordinary/partial differential equations. I will focus on differential equations in this short presentation. The simplest way to bake information about a differential equation with neural networks is to create a regularization term for the loss function used in training. I will explain the mathematics of this idea. I will also talk about applying physics-informed neural networks to a plethora of applications spanning the range from solving differential equations for all possible parameters in one sweep (e.g., solve for all boundary conditions) to calibrating differential equations using data to design optimization. Then, we will work on a hands-on activity that shows you to implement the ideas in PyTorch. I am assuming some familiarity with how conventional neural networks are trained (stochastic gradient descent). Also, you need to know the basics of PyTorch to follow along. Going over this tutorial should be sufficient: https://pytorch.org/tutorials/beginner/pytorch_with_examples.html. Title: Batch Reification Fusion Optimization (BAREFOOT) Framework Date: June 2nd 2021, 1:30 PM - 2:30 PM EST Speaker: Richard Couperthwaite, Texas A&M University Register here (limited seats): https://nanohub.org/groups/ml/handsontraining Abstract: This tutorial will present the fundamentals of multi-fidelity fusion as well as Sequential and Batch Bayesian Optimization as possible optimization approaches that can be integrated with high accuracy computational models or experimental procedures to speed up the optimization or design of materials. The tutorial will also provide an overview of the BAREFOOT framework that combines these two approaches together to further improve the rate of the optimization. All these approaches are compared using the optimization of the workability of a dual-phase steel microstructure. Alejandro Strachan Deputy Director, nanoHUB (2020 R&D 100 winner) -- Alejandro Strachan Professor of Materials Engineering, Purdue University Network for Computational Nanotechnology - nanohub.org<http://nanohub.org> Center for Predictive Materials and Devices (c-PRIMED)
participants (1)
-
Ku Blanco, Aury Y