Journals
  Publication Years
  Keywords
Search within results Open Search
Please wait a minute...
For Selected: Toggle Thumbnails
Research on High-Precision Stochastic Computing VLSI Structures for Deep Neural Network Accelerators
WU Jingguo, ZHU Jingwei, XIONG Xiankui, YAO Haidong, WANG Chengchen, CHEN Yun
ZTE Communications    2024, 22 (4): 9-17.   DOI: 10.12142/ZTECOM.202404003
Abstract16)   HTML0)    PDF (1890KB)(8)       Save

Deep neural networks (DNN) are widely used in image recognition, image classification, and other fields. However, as the model size increases, the DNN hardware accelerators face the challenge of higher area overhead and energy consumption. In recent years, stochastic computing (SC) has been considered a way to realize deep neural networks and reduce hardware consumption. A probabilistic compensation algorithm is proposed to solve the accuracy problem of stochastic calculation, and a fully parallel neural network accelerator based on a deterministic method is designed. The software simulation results show that the accuracy of the probability compensation algorithm on the CIFAR-10 data set is 95.32%, which is 14.98% higher than that of the traditional SC algorithm. The accuracy of the deterministic algorithm on the CIFAR-10 dataset is 95.06%, which is 14.72% higher than that of the traditional SC algorithm. The results of Very Large Scale Integration Circuit (VLSI) hardware tests show that the normalized energy efficiency of the fully parallel neural network accelerator based on the deterministic method is improved by 31% compared with the circuit based on binary computing.

Table and Figures | Reference | Related Articles | Metrics
Technology Development and Deployment Strategy of Carrier Ethernet
Xu Xianghui, Chen Yunqing
ZTE Communications    2009, 7 (1): 36-39.  
Abstract73)      PDF (264KB)(116)       Save
Carrier Ethernet (CE ) is gradually stepping away from standardization and testing to deployment and application in live networks. Although great improvement has been made in the reliability of various CE technologies, there is need for improvement in their Quality of Service (QoS ), Operation, Administration and Maintenance (OAM ), especially the multi-vendor interoperability. The deployment of CE should be service-oriented, and the factors, such as maturity of related technologies and standards, deployment costs, and the complexity of network reconstruction as well as the interoperability with other vendors, should be taken into full consideration to flexibly select appropriate networking technology for different application scenarios according to technical features.
Related Articles | Metrics