tinyML Summit 2021 https://www.tinyml.org/event/summit-2021/
Partner Sessions – Processing Engines
System Level Energy Considerations for Battery Powered AI
Afshin NIKTASH, Senior Principal Software Engineer, Maxim Integrated
To bring complex AI inferencing to battery powered applications, several approaches are available to improve the energy consumption of convolutional neural network (CNN) computations. This presentation will overview the MAX78000 AI microcontroller and outline a number of system (not just ML) factors that can be considered to achieve audio and visual AI inferencing at battery power levels, and specific examples of face identification and keyword spotting will be highlighted.