Linear Model

Important Note: Original article http://ecdicus.com/linear-model/ Linear model is the most widely used model in machine learning. It refers to a model that uses linear combinations of sample features to make predictions. Where $\textbf{w} [w_1,…, w_D] T$ is the D-dimensional weight vector, and b is the bias. The linear regression introduced in the previous chapter is a typical linear model, and $f(\textbf{x};\textbf{w})$ is directly used to predict the output target $y f(\textbf{x};\textbf{w})$. In the classification problem, since the output target y is some discrete labels, and the value range of $f(\textbf{x};\textbf{w})$ is a real number,$f(\textbf{x};\textbf{w})$ cannot be directly used for prediction, and a non-linear decision function needs to be introduced g(.) to predict the output target Where, f(x;w) is also called Discriminant Function.