We have developed an innovative patent-pending hardware accelerator for Predictive AI Inference.  Our invention radically re-imagines the fundamental data flows of neural networks allowing these networks to go beyond current limitations. It decreases circuit complexity and therefore size, weight, power consumption, and cost while permitting model adjustments and improvements on the fly without retraining.

We are actively pursuing our go-to-market strategy across five target sectors:

• Defense:  Suites of cognitive sensors have become the mainstay of electronic warfare and signals intelligence but machine learning hardware has not kept pace. Our chip can.
• Financial markets:  Using our chip, quant and algo trading firms can dramatically improve, flex, and scale up their current AI/ML models to profit from overlooked alpha.
• Industrial process automation:  Our innovation lets us generate more accurate and useful real-time monitors that can pinpoint manufacturing problems as well as warn of imminent failures. Our first application is focused on pharmaceutical manufacturing. Marketing targets here are the established players in the SCADA industry.
• Healthcare: Continual patient status monitoring is the new standard-of-care, but too few institutions have this fully automated. Our chip solves this, requiring human intervention only to respond to alerts.
• Retail product line forecasting at scale: In a typical application, 200,000 SKUs and 2,000 stores must be analyzed, but these volumes can only be handled by today’s ML inference systems at aggregate levels. The problem is that aggregation negatively impacts accuracy. Our technology allows each SKU and store to be modeled independently.