Semi-Supervised Learning

Intermediate

Training with a small labeled dataset plus a larger unlabeled dataset, leveraging assumptions like smoothness/cluster structure.

Full Definition

Training with a small labeled dataset plus a larger unlabeled dataset, leveraging assumptions like smoothness/cluster structure.

Keywords

few labels consistency

Domains

Machine Learning

Related Terms

Machine Learning narrower than

A subfield of AI where models learn patterns from data to make predictions or decisions, improving with experience ra...

 Self-Supervised Learning related to

Learning from data by constructing “pseudo-labels” (e.g., next-token prediction, masked modeling) without manual anno...

 Online Learning related to

Learning where data arrives sequentially and the model updates continuously, often under changing distributions.

 Transfer Learning related to

Reusing knowledge from a source task/domain to improve learning on a target task/domain, typically via pretrained mod...

 Multitask Learning related to

Training one model on multiple tasks simultaneously to improve generalization through shared structure.

 Machine Learning related to

A subfield of AI where models learn patterns from data to make predictions or decisions, improving with experience ra...

 Supervised Learning related to

Learning a function from input-output pairs (labeled data), optimizing performance on predicting outputs for unseen i...

 Unsupervised Learning related to

Learning structure from unlabeled data, such as discovering groups, compressing representations, or modeling data dis...

Concept Map

See how Semi-Supervised Learning connects to other concepts.

Open Knowledge Graph