thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Intermediate

Regularization

Techniques that constrain model complexity to reduce overfitting.

Definition

Regularization adds a penalty or constraint that discourages the model from fitting noise. Examples include L1 and L2 penalties on weights, dropout, early stopping, data augmentation and limiting tree depth. The regularization strength is a hyperparameter tuned on validation data.

Exam tip

Increase regularization to fix overfitting; decrease it to fix underfitting.

Related terms