Completed
Can we Learn on the Edge? Al systems need to continually adapt to new data collected from the sensors Not only inference, but also run back-propagation on edge devices
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
On-Device Learning Under 256KB Memory - Challenges and Solutions for IoT Devices
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Can we Learn on the Edge? Al systems need to continually adapt to new data collected from the sensors Not only inference, but also run back-propagation on edge devices
- 3 #Activation is the Memory Bottleneck, not #Trainable Parameters
- 4 Related Work: Parameter-Efficient Transfer Learning
- 5 Address Optimization Difficulty of Quantized Graphs
- 6 QAS: Quantization-Aware Scaling
- 7 Sparse Layer/Tensor Update
- 8 Find Layers to Update by Contribution Analysis
- 9 Tiny Training Engine (TTE)
- 10 Tiny Training Engine Workflow
- 11 Deep Gradient Compression: Reduce Bandwidth
- 12 Post-training testing (high accuracy)
- 13 Real-life testing
