A class of Machine Learning (ML) that is becoming more and more attractive and challenging for ML is the edge ML or TinyML, where ML algorithms are compressed to run in resource-constrained microcontrollers. To allow to have effective tiny ML systems, on one side, hardware specialists are designing novel hardware architectures to deal with the demand for large computational and storage capability. On the other side, software and algorithms specialists, including Google, are proposing less complex models and sophisticated training tools. However, bringing tiny ML on a resource-constrained processor is still a very challenging task due to the limited memory and computational capabilities available in low-power processors. This talk will focus on Edge AI for a future generation of Smart IoT Devices that can process the information close to the sensors to improve energy efficiency and latency.

Download the slides for this talk.Download ( PDF, 12189.5 MB)