Hardware-aware neural architecture search and compression towards embedded intelligence
With the increasing availability of large-scale datasets and powerful computing paradigms, convolutional neural networks (CNNs) have empowered a wide range of intelligent embedded vision tasks, which span from image classification to downstream vision tasks, such as on-device object recognition, det...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Doctor of Philosophy |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/172506 |