***ATTENTION Indico Users***

Important changes to user logins are coming to Indico at BNL.

Please see the News section for more information.

6-15 December 2021
US/Eastern timezone

Machine learning and data science-driven techniques have proven to be transformative methods in the last decade. Lying at the heart of Brookhaven National Laboratory (BNL) and the Department of Energy's computational initiatives, we believe that the applications of these techniques have major potential in almost every field of science. To this end, the Computational Science Initiative (CSI) recently christened the Center for Computing Sciences Education and Support (CCSES) program to help enable BNL personnel and their collaborators leverage machine learning and data-driven methods to accelerate their own research. As one of the first efforts made by CCSES, we are excited to present the first of a three-part tutorial series on AI and machine learning. This first series, intended for beginners in software and/or machine learning, will cover the following introductory topics:

  1. Basic Python, including installation and usage
  2. Basic NumPy (numerical Python), including usage and best practices
  3. Introduction to Machine Learning 
  4. Introduction to automatic gradient-enabled tensors using PyTorch, and your first neural networks
  5. A first use case: convolutional neural networks for image classification

The intermediate and advanced tutorial series will be coming in the near future. 

The speakers for this beginner series are early-career researchers in CSI's machine learning group.


  • David Dakota Blair
  • Matthew Carbone
  • Yi Huang
  • Sandeep Mittal 
  • Yihui (Ray) Ren 

Organizing Committee:

  • Matthew Carbone 
  • Nicholas D'Imperio 
  • Meifeng Lin
  • Shinjae Yoo

Notice: This event falls under Exemption D (Formal classroom training held at Federal facilities, which does not exhibit indicia of a formal conference as outlined in the Conference/Event Exemption Request Form.) Participation is contingent on application acceptance.

Event ID: E000003974