Completed
tiny ML. Talks
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
System Support for Efficient Multi-Resolution Visual Computing on Mobile Systems
Automatically move to the next video in the Classroom when playback concludes
- 1 tiny ML. Talks
- 2 Vision doesn't always need high-resolution images
- 3 We can exploit this if image sensing is energy-proportional
- 4 Image sensor power breakdown
- 5 Idle power limits energy- proportionality
- 6 Driver-based power optimization: (1) Aggressive power management
- 7 Driver-based power optimization (2) Pixel clock frequency optimization
- 8 Energy-proportionality
- 9 However, resolution reconfiguration incurs latency penalty
- 10 Hardware is not the culprit
- 11 In the operating system, resolution reconfiguration undergoes a sequential procedure inside the media framework which requires the application to invoke several expensive system calls
- 12 Aspirations for a reconfigurable media framework
- 13 We introduce the Banner media framework
- 14 Parallel reconfiguration
- 15 Format-oblivious memory management
- 16 Banner media framework for seamless resolution reconfiguration
- 17 Ongoing efforts in multi-resolution visual computing systems
- 18 TinyML for all developers Dataset
- 19 Next tiny ML Talks
