利用Akida实现超低PowerEdge推理和OnDevice学习

brainchipInc © Enabling Ultra-Low Power Edge Inference and On-Device Learning with AkidaNandan NayampallyCMOBrainchip Inc.brainchipInc © •The Challenge•The Approach•The Delivery•The Results•Akida in actionAgenda2brainchipInc © The ChallengebrainchipInc © The Problem4$50BAnnual losses in Manufacturing due tounplanned downtime21TBData generated by 1 Car per day3$6MCosts of training a singleHigh-end model 1$1.1THealthcare cost and lost productivity due to preventable chronic disease44Courtesy: fightchronicdisease.org2Courtesy: Deloitte.com1Courtesy: Spectrum.Ieee.org. “The cost of training, made retraining the model infeasible” 3Courtesy: Forbes.combrainchipInc © The Opportunity5Image: Courtesy Pixabay(From MckinseyAIoT 2030 forecast)$15.7TGlobal GDP Benefit fromAI in 2030** PWC analysis report$1.2TAIoT revenue in 2030**** Forbes Business Insights1T+Edge devices in 2030**brainchipInc © The Challenge6Cost of cloud servicesResponsiveness & reduced latencyScalability & efficiencyPrivacy pr