Innatera books $21M in funding for its ultra-low-power AI chips

Netherlands-based microprocessor maker Innatera Nanosystems B.V. said it closed an oversubscribed $21 million Series A funding round, which included a $16 million investment the corporate announced in March and a further $5 million from latest investors.

The corporate’s Spiking Neural Processor T1, unveiled in January, is an energy-efficient artificial intelligence chip for sensor-edge applications. It incorporates a proprietary event-driven computing engine, a convolutional neural network accelerator and a RISC-V central processing unit (pictured) for running ultra-low-power AI applications on battery-powered devices.

Innatera, which was spun out of the Delft University of Technology in 2018, says it’s filling a spot out there for AI-powered devices that require human-machine interaction. Its chip is “mainly a brain-inspired processor that permits turnkey intelligence in applications where power is proscribed,” Chief Executive Officer Sumeet Kumar told SiliconANGLE in an interview. “It essentially means that you can analyze sensor data in real time by simulating how your brain recognizes patterns of interest.”

The corporate says the Spiking Neural Processor enables high-performance pattern recognition of images and spoken words on the sensor edge with submilliwatt power consumption and submillisecond latency. It claims its chips eat 500 times less energy and are 100 times faster than conventional microprocessors.

At all times-on operation

The analog-mixed signal neuromorphic architecture allows for the always-on operation needed in applications like security cameras and listening devices inside a narrow power envelope. The processors might be used as a dedicated sensor-handling engine that enables functions equivalent to conditioning, filtering and classification to be offloaded from a central processor or sent to the cloud.

“We tend to not concentrate on applications that require large format image processing,” Kumar said. “We’re most useful when there may be event data inside the information stream, or there’s something temporal equivalent to radar, low-resolution images, cameras and sensors.” A typical use case, he said, is a video doorbell that should be continuously awake but run on a chargeable battery.

“It’s mainly a neural network that understands time,” Kumar said. “By implementing this type of computation using analog circuits and mimicking the brain’s algorithms for pattern recognition, we got here up with an answer that’s about 10,000 times more efficient at detecting patterns and sensor data in comparison with traditional microcontrollers.”

Just like a field programmable gate array, he said, “it consists of computational elements whose connectivity and parameters might be programmed at runtime. It may flexibly implement any neural network that you may train in your desktop.”

AI framework support

As a microcontroller, the processor has no operating system, but Innatera has a software development kit and firmware that runs applications inbuilt PyTorch, with support for added AI frameworks planned. “You construct a brand new training model in a well-recognized framework, after which once that model is trained, you may map it onto the chip without having to know any of what goes on contained in the chip,” Kumar said.

The processors, the results of six generations of silicon design, are expected to ship in limited volume by the tip of the yr and at full volume in 2025.

Innatera employs about 75 people today and built its first processors with lower than $5 million of investment. “We’ve been tremendously capital-efficient,” Kumar said.

The corporate plans to make use of the funding to get its first product into large-scale production in 2025 and expand marketing and sales. A Series B funding round is planned inside the following yr.

The Series A extension was led by Innavest and Invest-NL N.V., who joined existing Series A investors, which included the European Commission’s EIC Fund, MIG Capital LLC, Matterwave Ventures Management GmbH and Delft Enterprises B.V.

Image: Innatera