Innatera Nanosystems is a spin-off of the Delft University of Technology in the Netherlands and developed a neuromorphic chip that mimics the brain’s mechanisms for pattern recognition. This enables sensor data to be processed 100x faster and with up to 500x less energy than with conventional processors.
Target applications include intelligent speech processing in human-machine interfaces, vitals monitoring in wearable devices, target recognition in Radars and Lidars, and fault detection in industrial and automotive equipment.
The technology relies on new analog-mixed signal devices that recreate the behaviour of the brain’s fundamental building blocks – spiking neurons and synapses. Neural networks built with spiking neurons possess a precise notion of time which enables them to be a factor of 10-100x more compact than conventional artificial neural networks, especially for applications involving data with high spatial and temporal correlations.
The €5m seed investment round was led by Munich-based fund MIG Verwaltungs and the Industrial Technologies Fund of venture capital group btov Partners.
Innatera is working on a suite of proprietary algorithms and an extensive software toolchain for developers to use the neuromorphic silicon. The investment will enable the company to scale up its R&D efforts and accelerate product development to deliver on customer commitments through 2021 as well as hire more staff.
“Innatera sets itself apart from the plethora of AI accelerator companies by focussing on the edge of the edge – sensory data processing in the field,” said Dr Christian Reitberger, Partner at btov. “Translating truly brain inspired design principles into state of the art analog-mixed signal solutions enables a performance envelope not accessible to more conventional solutions.”
Edge computing is gaining traction across domains including consumer electronics, IoT, smart industry, and automotive. IDC forecasts the edge AI processor market to reach the $40bn revenue mark by 2023. The market is expected to grow with a CAGR of over 85 percent as vendors integrate more AI-driven functionalities closer to sensors due to requirements for