When it comes to AI, can we ditch the datasets? : vimarsana.

When it comes to AI, can we ditch the datasets?

MIT researchers have developed a technique to train a machine-learning model for image classification, which does not require the use of a dataset. Instead, they use a “generative model” to produce synthetic data that is used to train an image classifier, which can then perform as well as or better than an image classifier trained using real data.

Related Keywords

United States , Ali Jahanian , Xavier Puig , Phillip Isola , International Conference On Learning Representations , Artificial Intelligence Laboratory , Watson Ai Lab , United States Air Force Artificial Intelligence Accelerator , Department Of Electrical Engineering , United States Air Force Research Laboratory , Computer Science , Yonglong Tian , Electrical Engineering , International Conference , United States Air Force Artificial Intelligence , Enerative Models Training , Contrastive Learning ,

© 2025 Vimarsana