Exploring Accumulated Gradient-Based Quantization and Compression for Deep Neural Networks
The growing complexity of neural networks makes their deployment on resource-constrained embedded or mobile devices challenging. With millions of weights and biases, modern deep neural networks can be computationally intensive, with large memory, power and computational requirements. In this thesis,...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Others |
| Published: |
Virginia Tech
2020
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10919/98617 |