Intelligent MEMS Sensors with On-Sensor Tiny Machine Learning

Abstract
Smart sensors enable a distributed computing approach which significantly reduces the bandwidth requirement for transferring sensor data when the edge computing capabilities in microcontrollers or sensors are utilized. MEMS sensors are now commercially available with a built-in Machine Learning Core (MLC), Finite State Machine (FSM) and Intelligent Sensor Processing Unit (ISPU). These sensors can execute decision trees, neural networks, and symbolic logic directly on the MEMS sensor die. This capability allows the user to develop a variety of applications for consumer, industrial, automotive or medical devices where power consumption for applications needs to be minimized. This presentation will focus on all aspects of on-sensor machine learning that are increasingly being used to build solutions with an always-on user experience with extremely low current consumption, in order of single-digit micro-amps for MEMS sensor applications.
Speaker(s): Dr. Mahesh Chowdhary
Agenda:
6:30 – 7:00 PM Registration & Networking
7:00 – 7:45 PM Invited Talk
7:45 – 8:00 PM Questions & Answers
Room: Geneva and Grenoble Conference Rooms, Bldg: 3rd Floor, STMicroelectronics, 2755 Great America Way, Santa Clara, California, United States, 95054, Virtual: https://events.vtools.ieee.org/m/415057