Energy-efficient On-device Processing for Next-generation Endpoint ML - tinyML Summit 2020

Energy-efficient On-device Processing for Next-generation Endpoint ML - tinyML Summit 2020

tinyML via YouTube Direct link

Example: Typical ML Workload for a Voice Assistant

13 of 13

13 of 13

Example: Typical ML Workload for a Voice Assistant

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Energy-efficient On-device Processing for Next-generation Endpoint ML - tinyML Summit 2020

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Best-in-class Solution Optimized for Endpoint Al
  3. 3 Unified Software Development: Fastest Path to Endpoint Al
  4. 4 Cortex-M55:The most Al-capable Cortex-M CPU
  5. 5 Simplified Software Development Based on a Unified Programmer's View
  6. 6 Cortex-M55 and CMSIS-NN performance results
  7. 7 Ethos-U55 overview
  8. 8 Typical Ethos-U55 data flow
  9. 9 Ethos-U55 interfaces
  10. 10 Mapping of NNs to Hardware using TensorFlow Lite
  11. 11 An example smart speaker pipeline
  12. 12 Throughput-smart speaker use case
  13. 13 Example: Typical ML Workload for a Voice Assistant

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.