An AI Watched 600 Hours of TV and Started to Accurately Predict What Happens Next


MIT's Computer Science and Artificial Intelligence Laboratory created an algorithm that utilizes deep learning, which enables artificial intelligence (AI) to use patterns of human interaction to predict what will happen next. Researchers fed the program with videos featuring human social interactions and tested it to see if it "learned" well enough to be able to predict them. While this lineup may seem questionable, MIT doctoral candidate and project researcher Carl Vondrick reasons out that accessibility and realism were part of the criteria. "We just wanted to use random videos from YouTube," Vondrick said. "The reason for television is that it's easy for us to get access to that data, and it's somewhat realistic in terms of describing everyday situations."

Duplicate Docs Excel Report

None found

Similar Docs  Excel Report  more

None found