AIStorm raises funds to commercialise AI-in-sensor chips

1 min read

AIStorm, an innovator of high-performance AI-in-Sensor processors, has announced that it has closed $16 million in an oversubscribed Series B financing round from strategic investors.

Investors included: AsusTek, a manufacturer of computing equipment; Egis Technology, a biometrics supplier; Knowles, a market leader in advanced micro-acoustic microphones; Meyer Corporation, a supplier of food-preparation equipment; and Senvest Management, a New York-based venture capital firm.

AIStorm is looking to target a range of applications where its technology offers a number of advantages: imaging and audio, facial recognition, access control, behavioral tracking, people counting, face detection, object tracking, and segmentation.

“AIStorm’s approach is the only technology that allows the sensor to couple directly to popular convolutional neural networks. This allows AIStorm to deliver true, template-based ‘always-on’ at the edge, at prices that deep-submicron digital competitors cannot match for the same performance. This is a winning formula in the highly competitive IoT sector,” said David Schie, CEO of AIStorm.

AIStorm has partnered with a number of companies that are leaders in their respective markets: AsusTek is a leader in laptops and residential IoT devices; likewise, Egis in biometric sensing, with its chips used by most of the major handset makers worldwide; Knowles in advanced micro-acoustic microphones and the Meyer Corporation is a leader in cookware and food-processing equipment

“AIStorm’s charge-switched analogue computing, coupled with its AI-in-Sensor approach, offers dramatic advantages for ultra-low power, ultra-low-latency AIoT edge computing. We look forward to an ongoing strategic collaboration,” said Jonney Shih, chairman of AsusTek.

AIStorm’s charge-domain processing approach differs from solutions used by ARM licensees, FPGAs, or vendors of process-in-memory solutions. It accepts charge directly from the sensor, such as electrons from a pixel or MEMs microphone, and multiplies that charge directly.

According to AIStorm, its partners benefit from an AI-at-the-edge technology that is scalable, offers MAC efficiencies up to several thousand TOPS per watt, and works with conventional tool flows.

“Offering true CNN functionality and requiring a minimum of external components, AIStorm’s solutions are well positioned to dominate the AI edge space, especially in always-on, battery-operated applications such as cell phones, TV remotes, laptops, home security, and authentication,” said Nav Sooch, founder and chairman of Silicon Labs.