Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

Chapter 1: Introduction to Supervised Learning

SectionsΒΆ

SummaryΒΆ

1.1 What is Machine Learning?ΒΆ

1.2 Squared Loss and the Constant ModelΒΆ

1.3 Absolute LossΒΆ

1.4 Comparing Loss FunctionsΒΆ

LossL(yi,w)L(y_i, w)wβˆ—w^*Always unique?Robust to outliers?
squared(yiβˆ’w)2(y_i - w)^2meanyesno
absolute∣yiβˆ’w∣\lvert y_i - w \rvertmediannoyes
LpL_p as pβ†’βˆžp \to \infty∣yiβˆ’w∣p\lvert y_i - w \rvert^pmidrange min⁑+max⁑2\frac{\min + \max}{2}yesno
0-10 if yi=wy_i = w, else 1modenono