Perceptron and Generalized Linear Model
Perceptron Perceptron algorithm is not something that is widely used in practice. We study it mostly for historical reasons. And also it’s nice and simple, and easy to analyze. As you know, Logistic Regression uses the Sigmoid Function. Which essentially squeezes the entire real line, from $-\infty$ to $+\infty$, between 0 and 1, and the 0 and 1 kind of represent the probability of the output being 1. ...