33
/fr/
AIzaSyB4mHJ5NPEv-XzF7P6NDYXjlkCWaeKw5bc
November 1, 2025
3255110
288434
1
Create a timeline
Public Timelines
For education
For educational institutions
For teachers
For students
Cabinet
For educational institutions
For teachers
For students
Open cabinet
FAQ
Obtenir le Premium
Close
Create a timeline
Public timelines
FAQ
About & Feedback
Un accord
Confidentialité
FAQ
Support 24/7
Cabinet
Get premium
Donate
2 janv. 2018 - Deep Neural Network Compression with Single and Multiple Level Quantization
Description:
本文首次同时在宽度和深度上进行量化,SLQ/MLQ。首先在宽度上,使用SLQ,将权值划分为量化部分和重训练部分,通过重训练部分降低量化损失。在深度上,使用MLQ,通过将损失累计到下一层迭代,以降低当前层的量化损失。
Ajouté au bande de temps:
Quantization timeline
By
龚成
29 mars 2020
1
0
809
Date:
2 janv. 2018
Maintenaint
~ Il y a 7 ans et 9 mois
About & Feedback
Un accord
Confidentialité
FAQ
Support 24/7
Cabinet
Get premium
Donate
The service accepts bank transfer (ACH, Wire) or cards (Visa, MasterCard, etc). Processed by Stripe.
Secured with SSL