Certified quantization strategy synthesis for neural networks
Quantization plays an important role in deploying neural networks on embedded, real-time systems with limited computing and storage resources (e.g., edge devices). It significantly reduces the model storage cost and improves inference efficiency by using fewer bits to represent the parameters. Howev...
Saved in:
Main Authors: | ZHANG, Yedi, CHEN, Guangke, SUN, Jun |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9325 https://ink.library.smu.edu.sg/context/sis_research/article/10325/viewcontent/978_3_031_71162_6_18_pvoa_cc_by.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
In-network join processing for sensor networks
by: YU, Hai, et al.
Published: (2006) -
On in-network synopsis join processing for sensor networks
by: YU, Hai, et al.
Published: (2006) -
Evidence aware neural pornographic text identification for child protection
by: SONG, Kaisong, et al.
Published: (2021) -
Visualizing and querying semantic social network
by: SUN, Aixin, et al.
Published: (2011) -
Neural multimodal belief tracker with adaptive attention for dialogue systems
by: ZHANG, Zheng, et al.
Published: (2019)