Machines Learn Like Humans Thanks To New Algorithm

Share Tweet Share Share Email Computer scientists from New York University, MIT and the University of Toronto have developed a new computer algorithm allows computers to not only recognize, but draw draw basic visual concepts with an accuracy that is hardly distinguishable from human works. The advancement marks a major breakthrough in the field of computer learning, as it allows for more creative tasks — effectively broadening the scope of what can be achieved with computers. The paper’s lead author, NYU’s Brenden Lake, explained that their findings, which were published in the journal Science, “show that by reverse engineering how people think about a problem, we develop better algorithms,” which points towards “promising methods” for speeding up other machine learning tasks. Our results show that by reverse engineering how people…

Link to Full Article: Machines Learn Like Humans Thanks To New Algorithm

Pin It on Pinterest

Share This

Join Our Newsletter

Sign up to our mailing list to receive the latest news and updates about and the Informed.AI Network of AI related websites which includes Events.AI, Neurons.AI, Awards.AI, and Vocation.AI

You have Successfully Subscribed!