Machine Learning · Level 2 of 5
Semi-supervised Learning
Learning from a mixture of labeled and unlabeled examples.
Unlabeled data can help when the method's assumptions match the data.
Example
A classifier uses a small labeled photo set and many unlabeled photos.
Listen to the definition and example
Audio transcript
Semi-supervised Learning. Learning from a mixture of labeled and unlabeled examples. Unlabeled data can help when the method's assumptions match the data. For example: A classifier uses a small labeled photo set and many unlabeled photos.
Explore this concept
Why it matters
This helps you choose and evaluate a learning setup that matches the data and task.
Start with
Quick recall question
Try answering before looking back at the definition.