7 · Logistic Regression

Transitioning to classification — why linear regression fails on discrete targets, the mathematical necessity of the sigmoid curve, and the mechanics of binary and multiclass decision boundaries.

📄️Why Logistic Regression

Binary classification setup; why linear regression fails on classification; why the sigmoid function is needed

📄️The Sigmoid and Fitting

Deriving the sigmoid fit from the linear equation; working through hand calculations; log loss as the cost function

📄️Multiclass and Practical Use

Extending binary logistic regression to >2 classes (one-vs-rest, softmax); decision boundaries; practical API usage