Semi-Supervised Learning

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

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

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

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

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

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

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

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