Completed
Enabling the next generation of Sensor and Hearable pro to process rich data with energy efficiency
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
TinyML Talks - Demoing the World’s Fastest Inference Engine for Arm Cortex-M
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 tinyML Summit 2022 Miniature dreams can come true. March 28-30, 2022 Hyatt Regency San Francisco Airport
- 3 You might know us from: Person detecti Person Presence Detection
- 4 Or from: the world's fastest Cortex-M inferen
- 5 How did we get here?
- 6 The machine learning flow
- 7 The tasks of an inference engine
- 8 An inference engine example: TELM
- 9 A closer look at the results
- 10 More off-the-shelf models
- 11 A closer look at the MLPerf Tiny models
- 12 How to beat the competition?
- 13 Memory planning: a (rotated) game of T
- 14 Memory planning for an example model
- 15 A much better memory plan
- 16 Even better: lower granularity planning
- 17 Memory planning at Plumerai: summary
- 18 Optimized INT8 code for speed
- 19 Model-specific code generation
- 20 The world's fastest Cortex-M inference
- 21 What can Plumerai mean for you?
- 22 Public benchmarking service: try it yours
- 23 Arm: The Software and Hardware Foundation for tin
- 24 EDGE IMPULSE The leading edge ML pla
- 25 Enabling the next generation of Sensor and Hearable pro to process rich data with energy efficiency
- 26 maxim integrated Maxim Integrated: Enabling Edge Intelligence
- 27 BROAD AND SCALABLE EDGE COMPUTING PORTFOLIO
- 28 SYNTIANT
