Next-gen edge AI SoC for flagship devices

August 31, 2020 //By Peter Clarke
Kneron upgrades AI processor, adds distributed mesh processing
Kneron Inc. (San Diego, CA), an AI processor developer backed by Qualcomm and Alibaba among others, has launched its KL720 AI chip and added local mesh processing.

Kneron's KL720 AI chip achieves 1.5 TOPS in performance at 1.2W and uses a Cortex-M4 as its main control unit. This performance allows it to address AI around high-resolution images and audio processing.

"Its low cost enables even more devices to take advantage of the benefits of edge AI, protecting user privacy, to an extent competitors can't match," said Kneron founder and CEO Albert Liu. "Combined with our existing KL520, we are proud to offer the most comprehensive suite of AI chips and software for devices on the market."

The KL720 builds out from the KL520, which was based on two ARM Cortex-M4 processor cores and is intended to operate as either a host or companion AI co-processor enabling edge AI on devices like smart locks, security cameras, drones, smart home appliances, and robotics. It is compatible with various 3D sensor technologies such as Structured Light, dual-cameras, ToF camera, and Kneron’s own exclusive 3D sensing technology.

Kneron has also introduced something called Kneron neural network edge AI open platform, or Kneo for short. This is a private mesh network made up of Kneron-powered equipment that uses block-chain technology to secure the network and support sensor fusion.

The idea is that two or more sensors (cameras, mics, thermal sensors, etc) connect together to build a private edge mesh intelligence that doesn't need access to the cloud to process AI models and applications.

Kneron added $40 million to its Series A round of finance in January 2020 bringing the total to $73 million for its AI chip development. The round was led by Horizons Ventures of Hong Kong and included previous investors Qualcomm and Alibaba.

www.kneron.com

Related AI  articles:


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.