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

Semi-Supervised Learning

Learning that combines a small labeled dataset with a large unlabeled dataset to improve model accuracy.

Definition

Semi-supervised learning is useful when labeling is expensive but raw data is plentiful. Techniques include pseudo-labeling, where a model trained on labeled data assigns labels to unlabeled examples that are then used for further training. It sits between supervised and unsupervised learning.

Example

Labeling 1,000 medical images by hand and pseudo-labeling 100,000 more to train a classifier.

Exam tip

Choose semi-supervised when the question stresses that only a fraction of the data is labeled.

Related terms