Discussions

You can download the discussions here. We will try to upload discussion material prior to their corresponding sessions. Future discussions listed below likely have broken links.

• 

  Discussion_01 - SCC and Environment Setup
  tl;dr: Setting up SCC, virtual environments, and running jobs.
  [slides]
  

  Notebook: 00_fundamentals.ipynb
  Suggested Readings:

  • SCC Resources
  • Introduction to Pytorch
  • What’s a Tensor? - Dan Fleisch
  • Pytorch Internals - Edward Z. Yang
• 

  Discussion_02 - SCC Part 2 + Common Practices in Structuring DL Code + Examples to try out qsub and qrsh
  tl;dr: Running Jobs, Structuring Code, and Examples to try out qsub and qrsh. High-level overview of different components of a deep learning project. Will go more in-depth in future discussions.
  [Interactive Job (qrsh) walkthrough] [Non-Interactive Job (qsub) Example] [Job Array Example]
  

  Suggested Readings:

  • Introduction to Pytorch
  • What’s a Tensor? - Dan Fleisch
  • Pytorch Internals - Edward Z. Yang
• 

  Discussion_03 - Loss Functions, Activation Functions, Basic PyTorch components for building a model
  tl;dr:
  [Notebook]
  
• 

  Discussion_04 - Autograd and Automatic Differentiation in PyTorch
  tl;dr:
  [Notebook]
  
• 

  Discussion_05 - Weight Initialization, Data Loader, and Training Loop
  tl;dr:
  [Notebook]
  
• 

  Discussion_05 - Regularization
  tl;dr:
  [Notebook]