Home > News content

Facebook build autonomous chip for analyzing and filtering video content

via:博客园     time:2018/5/26 12:40:01     readed:316

Jain, chief artificial intelligence scientist at social networking giant Facebook


Photo: Mark, Facebook Chief Executive Officer, May 1, 2018

The traditional method is no longer effective, because the analysis and filtering of video content require more energy and computing power. In April, Bloomberg reported that Facebook was developing its own processor.

Recently posted a post on Intel AI DevCon as Director of Engineering, Kim.

Facebook also uses various forms of computer vision technology to review content, such as removing the propaganda content of terrorist organizations such as ISIS.

Graphics processing units (GPU) such as AMD and NVIDIA can help to rapidly increase unlabeled data, such as images and videos. Google continues to speed up AI training and deployment through its tensor processing unit (TPU), and Intel's field programmable gate array (FPGA) chip Stratix 10 is being used for the Microsoft's Project Brainwave project.

It is reported that apple, Google and Amazon also plan to launch specialized chips to help speed up the AI services on their hardware products.

China IT News APP

Download China IT News APP

Please rate this news

The average score will be displayed after you score.

Post comment

Do not see clearly? Click for a new code.

User comments