It refers to the training algorithms for machine learning using a minimal set of training data rather than an extensive set. This is most appropriate in the field of computer vision, where it is desirable to have a model of object categorization work well without thousands of examples of training.
World-class articles, delivered weekly.
See Akira AI in action
We transform large organizations around the world by translating cutting-edge AI
research into customizable, scalable and human-centric AI products.