few-shot learning
A machine learning approach, often used for object classification, designed to train effective classification models from only a small number of training examples.
Plain English Explanation
A machine learning approach, often used for object classification, designed to train effective classification models from only a small number of training examples. See also one-shot learning and zero-shot learning.
How is it used?
Practitioners refer to few-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.