Oct 16 2024

  • Former business school classmate, but also developer, took this class and recommended it
  • He sent along some primers on Linear Algebra and Probability
  • I wrongly read the Probability one first, and then after reading the Linear Algebra primer it was obvious after page 2 that I read them out of order
  • Linear Algebra - I’ve been helping my high school son with his math for years (I’ve had a lot of math as an engineer at Lehigh) but I had this thread going in the back of my head saying, “Do I need to learn this, and if so, then how deeply?”
  • I needed a break and was looking at some other resources for learning AI/ML, that led me to this set of YouTube videos, the first one here: Linear Algebra - Math for Machine Learning
    • Wow, this video really started to connect the dots on what I was reading in these primers and helped me as a developer to understand the analogous meanings of models, inputs/outputs, etc.
      • Many objects are represented by arrays in machine learning:
        • Almost always: data (inputs and outputs)
        • Very often: models (equivalent to programs)
        • Often: internal computations of models (local variables)
  • “Do I need to learn this?” → yes
    • I’m more motivated now to read this primer
  • “If so, then how deeply?” → TBD…I am pretty sure this is going to be a circuitous journey on math depth, not a linear one.