zero-shot learning
A type of machine learning training where the model infers a prediction for a task that it was not specifically already trained on.
Plain English Explanation
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.
How is it used?
Practitioners refer to zero-shot learning when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.