Also known as: Zero shot Learning Β· Zero Shot Learning
Zero-shot learning is a machine learning capability in which a model performs a task or recognizes a category without task-specific training examples. It relies on general knowledge, learned representations, or relationships from prior training to generalize to unseen tasks or concepts. In some contexts, the term is used more narrowly for extracting or classifying information without annotated examples.
A type of machine learning training where the model infers a prediction for a task that it was not specifically already trained on. In other words, the model is given zero task-specific training examples but asked to do inference for that task.