4 lessons
Vectors and the dot product
Why ML represents everything as lists of numbers, and the one operation (the dot product) that shows up in almost every model.
Derivatives and gradients, without the fear
What a slope actually measures, why it tells you which way to move, and how gradient descent turns that into a training algorithm.
Probability, conditional probability, and Bayes' theorem
What a probability actually is, how to combine and update them, and the theorem that powers an entire family of classic ML models.
Descriptive statistics and feature scaling
Mean, median, variance, correlation, and why almost every model needs its input features rescaled before training.