One of the godfathers of deep learning pulls together old ideas to sketch out a fresh path for AI, but raises as many questions as he answers.
Around a year and a half ago, Yann LeCun realized he had it wrong.
LeCun, who is chief scientist at Meta’s AI lab and one of the most influential AI researchers in the world, had been trying to give machines a basic grasp of how the world works—a kind of common sense—by training neural networks to predict what was going to happen next in video clips of everyday events. But guessing future frames of a video pixel by pixel was just too complex. He hit a wall.
Now, after months figuring out what was missing, he has a bold new vision for the next generation of AI. In a draft document shared with MIT Technology Review, LeCun sketches out an approach that he thinks will one day give machines the common sense they need to navigate the world. (Update: LeCun has since posted the document online.)
For LeCun, the proposals could be the first steps on a path to building machines with the ability to reason and plan like humans—what many call artificial general intelligence, or AGI. He also steps away from today’s hottest trends in machine learning, resurrecting some old ideas that have gone out of fashion.
To continue reading this article, click here.