Public Timelines

For educational institutions For teachers For students Cabinet

For educational institutions For teachers For students Open cabinet

FAQ Das Premium bekommen

Create a timeline

Public timelines

About & Feedback Vereinbarung Privatheit FAQ

Cabinet Get premium

Donate

20 Okt 2016 Jahr - Philipp Gysel: Hardware-oriented Approximation of Convolutional Neural Networks

Beschreibung:

本文实现了动态定点数的量化。针对激活值，卷积权值和全连接权值的差异，分别实现不同的动态定点数量化，像相同位宽下实现了更低的精度下降，但是其在低位宽的表现不好。

Zugefügt zum Band der Zeit:

Quantization timeline

29 Mär 2020

1

0

809

Datum:

20 Okt 2016 Jahr

Jetzt

~ 9 years ago

About & Feedback Vereinbarung Privatheit FAQ

Cabinet Get premium

Donate

The service accepts bank transfer (ACH, Wire) or cards (Visa, MasterCard, etc). Processed by Stripe.

Secured with SSL