30
/pt/
AIzaSyAYiBZKx7MnpbEhh9jyipgxe19OcubqV5w
April 1, 2024
3255110
288434
1
Public Timelines FAQ
Public TimelinesFAQ
Public TimelinesFAQ
For educational institutions For teachers For students Open cabinet
For educational institutions For teachers For students Open cabinet
Criar
Create a timeline
Public timelines
Library
FAQ

2 jan 2018 ano - Deep Neural Network Compression with Single and Multiple Level Quantization

Descrição:

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。

Adicionado na linha do tempo:

Quantization timeline

By龚成
29 mar 2020

Data:

2 jan 2018 ano
Agora
~ 6 years and 4 months ago
About & FeedbackAcordoPrivacidadeBiblioteca
2024 © Time.Graphics
Support 24/7  
CabinetGet premium
Donate
The service accepts bank transfer (ACH, Wire) or cards (Visa, MasterCard, etc). Processed by Stripe.
Secured with SSL
Excellent (Trustpilot Reviews)
Based on 115+ reviews
Write your own review on Trustpilot.com