Zobrazeno 1 - 10
of 114
pro vyhledávání: '"mixed-precision quantization"'
Publikováno v:
IEEE Access, Vol 12, Pp 137439-137454 (2024)
Split computing (SC) is an emerging technique to perform the inference task of deep neural network (DNN) models using both mobile devices and cloud/edge servers in a hybrid manner. To improve the end-to-end inference time over the network, SC splits
Externí odkaz:
https://doaj.org/article/c62de56e292744699dffaaa690c4be88
Autor:
Luca Urbinati, Mario R. Casu
Publikováno v:
IEEE Access, Vol 12, Pp 44163-44189 (2024)
Precison-scalable (PS) multipliers are gaining traction in Deep Neural Network accelerators, particularly for enabling mixed-precision (MP) quantization in Deep Learning at the edge. This paper focuses on the Sum-Together (ST) class of PS multipliers
Externí odkaz:
https://doaj.org/article/3e0143af0bda4fb68c31d55f1e71cbe4
Autor:
Chun YANG, Ruiyao ZHANG, Long HUANG, Shutong TI, Jinhui LIN, Zhiwei DONG, Songlu CHEN, Yan LIU, Xucheng YIN
Publikováno v:
工程科学学报, Vol 45, Iss 10, Pp 1613-1629 (2023)
The study of deep neural networks has recently gained widespread attention in recent years, with many researchers proposing network structures that exhibit exceptional performance. A current trend in artificial intelligence (AI) technology involves u
Externí odkaz:
https://doaj.org/article/090861aed6144c0c89407af3dc96496c
Publikováno v:
Journal of Cloud Computing: Advances, Systems and Applications, Vol 12, Iss 1, Pp 1-16 (2023)
Abstract With the development of deep neural network (DNN) techniques, applications of DNNs show state-of-art performance. In the cloud edge collaborative mode, edge devices upload the raw data, such as texts, images, and videos, to the cloud for pro
Externí odkaz:
https://doaj.org/article/bf12e847683443868dbb3b2e28ec0e3b
Publikováno v:
IEEE Access, Vol 11, Pp 106670-106687 (2023)
Quantization, effective Neural Network architecture, and efficient accelerator hardware are three important design paradigms to maximize accuracy and efficiency. Mixed Precision Quantization is a process of assigning different precision to different
Externí odkaz:
https://doaj.org/article/2495076778684d1fa1f37f0873e6a844
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
ICT Express, Vol 8, Iss 3, Pp 322-327 (2022)
Driven by edge computing, how to efficiently deploy the meta-learner LSTM in the resource constrained FPGA terminal equipment has become a big problem. This paper proposes a compression strategy based on LSTM meta-learning model, which combined the s
Externí odkaz:
https://doaj.org/article/86d33a93b74f4812848ac6e40d3ac4a2
Autor:
CHANG Libo, ZHANG Shengbing
Publikováno v:
Xibei Gongye Daxue Xuebao, Vol 40, Iss 2, Pp 344-351 (2022)
To solve the problem of low computing efficiency of existing accelerators for convolutional neural network (CNNs), which caused by the inability to adapt to the characteristics of computing mode and caching for the mixed-precision quantized CNNs mode
Externí odkaz:
https://doaj.org/article/44c19b9e4a134a2c841407ac64db5810
Publikováno v:
Remote Sensing, Vol 15, Iss 16, p 4015 (2023)
Extensive research on deep neural networks for LiDAR point clouds has contributed inexhaustible momentum to the development of computer 3D vision applications. However, storage and energy consumption have always been a challenge for deploying these d
Externí odkaz:
https://doaj.org/article/b3208ef221fc4b628f93cc2bffc49a65