Artificial Intelligence Breakthrough: Training and Image Recognition on Low Power CPU (with no GPU), via Explainable-AI for Smart Appliance Pilot for Bosch – PRNewswire

Original article can be found here (source): artificial intelligence

POTOMAC, Md., March 23, 2020 /PRNewswire/ – Z Advanced Computing, Inc. (ZAC), the pioneer startup on Explainable-AI (Artificial Intelligence) (XAI), is developing its Smart Home product line through a paid-pilot for Smart Appliances for BSH Home Appliances (a subsidiary of the Bosch Group, originally a joint venture between Bosch and Siemens), the largest manufacturer of home appliances in Europe and one of the largest in the world.  ZAC just successfully finished its Phase 1 of the pilot program. “Our cognitive-based algorithm is more robust, resilient, consistent, and reproducible, with a higher accuracy, than Convolutional Neural Nets or GANs, which others are using now.  It also requires much smaller number of training samples, compared to CNNs, which is a huge advantage,” said Dr. Saied Tadayon, CTO of ZAC.  “We did the entire work on a regular laptop, for both training and recognition, without any dedicated GPU.  So, our computing requirement is much smaller than a typical Neural Net, which requires a dedicated GPU,” continued Dr. Bijan Tadayon, CEO of ZAC.  “Our solution requires much less electrical power, compared to the Neural Nets.  So, it can be used on portable devices or at edge, using just a battery,” explained Dr. Saied Tadayon.