[Workshop] tinyML Talks: Low-Power Computer Vision

Published: June 28, 2020 by SingularityKChen (Last updated: June 28, 2020 )

• Categories:
• Workshop 11

• Tags:
• HierarchicalNeuralNetwork 1
• tinyML 3

• tinyML Talks - Yung-Hsiang Lu: Low-Power Computer Vision
  • Hierarchical Neural Networks
  • The Existing Technologies for Making Computer Vision Energy-Efficient

tinyML Talks - Yung-Hsiang Lu: Low-Power Computer Vision¹

Hierarchical Neural Networks

By utilizing hierarchical neural network, we can separate the big neural network into much small ones, hence reduce the training time and inference power consumption. However, it might increase the latency.

The Existing Technologies for Making Computer Vision Energy-Efficient

This presentation also surveyed the existing technologies for making computer vision energy-efficient, including

1. parameter quantization and pruning;
2. compressed convolutional filters and matrix factorization;
3. network architecture search;
4. knowledge distillation.

1. tinyML, YouTube ↩