Spring 2024
CSC 578 Neural Networks and Deep Learning

1. Course Materials

• Assignments
  • Final Project (due 6/13 Thu)
  • Homework #7 (due 6/3 Mon)
  • Homework #6 (due 5/27 Mon) -- Quiz
  • Homework #5 (due 5/20 Mon)
  • Homework #4 (due 5/8 Wed)
  • Homework #3 (due 4/29 Mon)
  • Homework #2 (due 4/22 Mon) -- Quiz
  • Homework #1 (due 4/15 Mon) -- Quiz
  • Homework #0 (due 4/8 Sun) -- Quiz
  •    [Optional] Suggested Self-study (NOT to be submitted)

• Lecture Materials

• Syllabus & Schedule

• Textbooks

  • NNDL: Neural Networks and Deep Learning, by Michael Nielsen. Available for free online.
  • DLB: Deep Learning Book, by Goodfellow, Bengio, and Courville. MIT Press. Also available for free online, or bound from your favorite bookseller.

2. Course Resources

Cloud Development Environments:

• Google Colaboratory [instructions]- Similar to above, by Google.
• Kaggle [instructions]- Data Science competitions. Good source of sample datasets as well.
• Amazon EC2 instance

Tools:

• Numpy Quick Start, Tutorials
• More Numpy Quick Guide & Tutorials
• TensorFlow/Keras Tutorials - Google's mathematics package for deep learning.
• Keras Documentation -- With good example code too.
• Theano
• Juypter Notebooks - Easy to use environment that combines Python, Graphics and Text.

Videos:

• Gradient Descent (C1W2L04) by Andrew Ng
• Derivatives (C1W2L05) by Andrew Ng
• More Derivative Examples (C1W2L06) by Andrew Ng
• Computation Graph (C1W2L07) by Andrew Ng

3. Other Useful Stuff

• Differentiation Cheatsheet
• Calculus Refresher (section 9-14 most relevant)
• Useful Notations and Formulas (discrete math stuff)
• Algebra
  • Algebra Review (by Dr. Richard Johnsonbaugh)
  • A Quick Algebra Review
  • Good online tutorial (at West Texas A&M)