GENAIWIKI

Machine Learning

Zero-shot Learning

A machine learning approach where the model predicts classes that it has not seen during training.

Expanded definition

Zero-shot learning enables models to generalize and make predictions about new classes based on semantic relationships. By using auxiliary information, such as textual descriptions, these models can infer characteristics of unseen classes without direct training examples. This capability is particularly valuable in situations where collecting labeled data for every possible class is impractical.

Related terms

Explore adjacent ideas in the knowledge graph.