Using TensorFlow Lite for Microcontrollers for High-Efficiency NN Inference on Ultra-Low Power Processors
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore the use of TensorFlow Lite for Microcontrollers in high-efficiency neural network inference on ultra-low power processors in this 38-minute tinyML Talks webcast. Discover how specific hardware extensions on embedded processors can significantly improve the performance of neural network inference operations, allowing targets to be met while consuming less power. Learn about the integration of optimized neural network inference libraries with popular machine learning front-ends to facilitate development flows. Gain insights into the Synopsys MLI Machine Learning Inference library running on a DSP-enhanced DesignWare® ARC® EM processor through practical demonstrations, including a Person Detect Demo and a Deployable System Demo. Delve into topics such as optimizations, power considerations, edge developers, and programmability in the context of deeply-embedded AIoT applications.