AIStorm of San Jose, which uses analogue processing instead of GPUs for machine learning at the edge, has closed a $13.2 million in Series A financing from Egis Technology, TowerJazz, Meyer Corporation and Linear Dimensions Semiconductor.
“This investment will help us accelerate our engineering & go-to-market efforts to bring a new type of machine learning to the edge,” says CEO David Schie, “AIStorm’s revolutionary approach allows implementation of edge solutions in lower-cost analog technologies. The result is a cost savings of five to ten times compared to GPUs — without any compromise in performance.” The company’s first ICs, made on 65nm and 180nm processes, are scheduled for next year. AIStorm addresses the need to process sensor information at the edge to reduce the cost and security risk associated with transmitting large amounts of raw data from edge sensors.AI systems require information be available in digital form before they can process data, but sensor data is analogue. Processing this digital information requires advanced and costly GPUs that are not suitable for mobile devices: they require continuous digitization of input data, which consumes significant power and introduces unavoidable digitization delay. AIStorm aims to solve these problems by processing sensor data directly in its native analogue form, in real time.