BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal//recurring_events_ical//2.0//EN
BEGIN:VEVENT
UID:f010b6ac-f859-469a-b9f1-66b1b4a158fa@support.access-ci.org
DTSTAMP:20250311T175006Z
DTSTART:20250325T170000Z
DTEND:20250325T190000Z
SUMMARY:CI Pathways: Intro to PyTorch
DESCRIPTION:PyTorch is widely recognized for its flexibility and ease of us
 e, making it a top choice in both academic research and industry applicati
 ons. In this session, we will establish foundational concepts of neural ne
 tworks, understand their training process, and practice the concepts of au
 tomatic differentiation and backpropagation. Participants will gain an und
 erstanding of essential components of neural network training, such as los
 s functions, optimizers, and key architectural components. They will learn
  how to implement a basic neural network using PyTorch and train it on GPU
 s using the MNIST dataset. This training aims to build both theoretical kn
 owledge and practical skills, equipping participants to advance in the fie
 ld of deep learning.Pre-requisites:Basic Python programming, such as using
  NumPyBasic linear algebra (matrix-matrix multiplication)To participate in
  the hands-on exercises, you must know the basics of using NCSA's DeltaCI 
 Pathways is a training program led by the National Center for Supercomputi
 ng Applications and the Pittsburgh Supercomputing Center funded by NSF awa
 rd 2417789. For more information about the program, please visit the CI Pa
 thways webpage on HPC-Moodle.
URL:https://support.access-ci.org/events/7871
END:VEVENT
END:VCALENDAR