Facebook Aims To Advance AI By Creating Its Own Chips

Facebook Aims To Advance AI With Its Own Chips

Facebook wants to create its own chips to deliver the type of computing speeds necessary to take the next leap forward in artificial intelligence, according to a report in the Financial Times.

The company also wants to make a digital assistant – similar to Apple’s Siri or Amazon’s Alexa – that can have conversations with users and that has “common sense.”

Yann LeCun, the company’s chief AI scientist and a pivotal figure in modern AI, said the company also wants to use AI to help monitor video in real time and assist human moderators with content selection.

Though the company is working with chip companies like Intel on the new chips, it is not ruling out the possibility of developing its own.

Facebook has been known to build its hardware when required — build its own ASIC, for instance. If there’s any stone unturned, we’re going to work on it,” LeCun said.

Newer chips need to be specialized for things like lower power usage and lightning speed, as opposed to general processors of the past. Many companies, including Google and Apple, are investing in companies in the area of chip specialization.

LeCun said that taking big steps in AI requires huge hardware jumps. “For a fairly long time, people didn’t think about fairly obvious ideas,” he said.

For example, with more processing power came the process of back propagation, where deep learning systems go back over calculations to reduce errors. It’s now a common practice, but couldn’t have happened without a hardware jump in the ‘90s.

Facebook wants to create new software and then open-source it for others to work with and improve on. “The objective is to give it away,” LeCun said.

As for creating AI that has common sense, he acknowledges that it could take many years before that’s a reality.

“You want machines, like human beings or animals, to understand what will happen when the world responds to your interactions with it. There’s a lot of work we’re doing in causality,” he said. “Being able to predict under uncertainty is one of the main challenges today.”