Resources.md

Machine Learning Resources

• Linux
  • Shell - Lectures 1, 2 & 5¹
  • Vim
  • Git
  • Tmux
  • Debugging and Profiling - Lecture 7¹
  • More things to know
• Computer Science
  • How do computers read code?
• Python
  • Introduction to scientific packages
    • Numpy
    • Matplotlib
  • Jupyter notebook IDE
    • List of magics in jupyter-lab
  • Best practices
    • Joel Grus on - I don't like notebooks (Talk)
    • The Hitchhiker's Guide to Python
    • Type annotations - Joel Grus [Chapter 2]
    • Unit tests
• Computer vision
  • Introduction from first principles
• Information theory
  • Kullback-Leibler (KL) divergence - Chapter 3.13²
• Statistics
  • Covariance - Chapter 2.4.2³
• Data visualization
  • Contour plots
• Machine Learning

  • Kernel Density Estimation

  • What is Bayes theorem?

    • Conditional probability and Bayes rule - Chapter 3.1.3⁴
    • Medical test paradox

  • Probability density function

    • Binomial distribution - Chapter 1⁵
      • Intuition

  • Support vector machines

    • Theory - Chapters 6 & 7 ⁶
    • Intuition - Chapter 3.4, Chapter 8 ³

  • McCulloch and Pitts Neurons - Chapter 3.1.2³

  • Perceptron - Chapter 3³

  • Radial basis functions - Chapter 5³

  • Bias - variance tradeoff - Chapter 2.5r³

  • Deep Learning

    • Introduction - Chapter 1⁷
    • Stochastic gradient descent - Chapter 2.4⁷
    • Recurrent Neural Networks - Chapter 10⁷
      • Unreasonble effectiveness of RNNs (Blog Article)
    • Transformers
      • Intuition on Attention
    • Convolutional neural networks
      • What is convolution?
    • Frameworks
      • Tensorflow - Chapter 7⁷
        • Custom Models, Layers and Loss Functions
    • Large Language Models (LLMs)

  • Astronomy

    • Python for astronomy
      • Astropy
      • Tables
      • Tables (continued)
      • World Coordinate System (WCS)

Footnotes

1. Missing semester Playlist on youtube ↩ ↩²

2. Deep Learning by Ian Goodfellow , Yoshua Bengio ↩

3. Machine Learning: An Algorithmic Perspective by Stephen Marsland ↩ ↩² ↩³ ↩⁴ ↩⁵ ↩⁶

4. Statistics, Data Mining, and Machine Learning in Astronomy by Željko Ivezić, Andrew J. Connolly , Jacob T. VanderPlas & Alexander Gray ↩

5. Fundamentals of Statistical and Thermal Physics by F. Reif ↩

6. Pattern Recognition and Machine Learning by Christopher M. Bishop ↩

7. Deep Learning with Python by Francois Chollet ↩ ↩² ↩³ ↩⁴