Others can attend online over Webex. AI is slowing moving to IoT edge devices and pushing the limits and capacity of edge systems. Where there is an increased effort to improve hardware design considerations such as power, latency, throughput, cost, reliability, bandwidth, privacy and security with full support from economies/markets of scale, it still falls short on the demand. This talk will present the efforts at working on a compilers enabling machine learning models to perform on small formfactor like microcontrollers, which are part of all sorts of household devices: think appliances, cars, and toys. In fact, there are around 30 billion microcontroller-powered devices produced each year.