ML//logistic regression

Linear classifier: a weighted sum of features passed through a sigmoid to output a probability. Trained by minimizing cross-entropy.

Linear classifier: a weighted sum of features passed through a sigmoid to output a probability. Trained by minimizing cross-entropy.

Readable: the coefficients say how each feature pushes the odds, easy to sanity-check against domain knowledge.

The default scientific control before any deep model. If a small logistic model over hand-built features matches the network, the problem was mostly linear.

Cannot capture feature interactions on its own; that is where gradient boosting or a neural net can pull ahead.