Flexible Energy-Aware Image and Transformer Processors for Edge Computing
Machine learning inference on edge devices for image and language processing has become increasingly common in recent years, but faces challenges associated with high memory and computation requirements, coupled with limited energy resources. This work applies different quantization schemes and trai...
| 1. Verfasser: | |
|---|---|
| Weitere Verfasser: | |
| Format: | Abschlussarbeit |
| Veröffentlicht: |
Massachusetts Institute of Technology
2023
|
| Online Zugang: | https://hdl.handle.net/1721.1/152854 https://orcid.org/0009-0000-7720-9951 |