C
Chao Wang
Researcher at University of Science and Technology of China
Publications - 242
Citations - 2389
Chao Wang is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Speedup & Field-programmable gate array. The author has an hindex of 20, co-authored 212 publications receiving 1796 citations. Previous affiliations of Chao Wang include Huawei.
Papers
More filters
Journal ArticleDOI
DLAU: A Scalable Deep Learning Accelerator Unit on FPGA
TL;DR: This paper designs deep learning accelerator unit (DLAU), which is a scalable accelerator architecture for large-scale deep learning networks using field-programmable gate array (FPGA) as the hardware prototype and employs three pipelined processing units to improve the throughput.
Proceedings ArticleDOI
Cambricon-s: addressing irregularity in sparse neural networks through a cooperative software/hardware approach
Zhou Xuda,Zidong Du,Qi Guo,Liu Shaoli,Chengsi Liu,Chao Wang,Xuehai Zhou,Ling Li,Tianshi Chen,Yunji Chen +9 more
TL;DR: A software-based coarse-grained pruning technique, together with local quantization, significantly reduces the size of indexes and improves the network compression ratio and a hardware accelerator is designed to address the remaining irregularity of sparse synapses and neurons efficiently.
Journal ArticleDOI
MALOC: A Fully Pipelined FPGA Accelerator for Convolutional Neural Networks With All Layers Mapped on Chip
TL;DR: A new architecture for FPGA-based CNN accelerator that maps all the layers to their own on-chip units and working concurrently as a pipeline is proposed, which can achieve maximum resource utilization as well as optimal computational efficiency.
Journal ArticleDOI
WGAN-Based Synthetic Minority Over-Sampling Technique: Improving Semantic Fine-Grained Classification for Lung Nodules in CT Images
Qingfeng Wang,Xuehai Zhou,Chao Wang,Zhiqin Liu,Jun Huang,Ying Zhou,Changlong Li,Hang Zhuang,Jie-Zhi Cheng +8 more
TL;DR: The experimental results suggest that the WGAN-based oversampling technique can synthesize helpful samples for the minority classes to assist the training of the CNN model and to boost the fine-grained classification performance better than the conventional data augmentation method and the two schemes of the GAN and DCGAN techniques do.
Journal ArticleDOI
Soft computing in big data intelligent transportation systems
TL;DR: Experimental results on the prototype system demonstrate NeverStop can efficiently facilitate researchers to reduce the average waiting time for vehicles, and a genetic algorithm illustrating how theaverage waiting time is derived is presented.