Yu Wang
Auto-generated profile, based on publicly available information

Yu Wang

Tsinghua University

Research Focus & Metrics

Academic Career Length

27Years (2000-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 July 2019 in Nature
Verified
Journal Article
Closed access
JPJing Pei
Jing Pei
LDLei Deng
Lei Deng
SSSen Song
Sen Song
MZMingguo Zhao
Mingguo Zhao
YZYouhui Zhang
Youhui Zhang
LSLuping Shi
Luping Shi

21 February 2016
Verified
Conference Paper
Open access
JQJiantao Qiu
Jiantao Qiu
JWJie Wang
Jie Wang
SYSong Yao
Song Yao
KGKaiyuan Guo
Kaiyuan Guo
BLBoxun Li
Boxun Li
HYHuazhong Yang
Huazhong Yang
In recent years, convolutional neural network (CNN) based methods have achieved great success in a large number of applications and have been among the most powerful and widely used techniques in computer vision. However, CNN-based methods are com-putational-intensive and resource-consuming, and thus are hard to be integrated into embedded systems such as smart phones, smart glasses, and robots. FPGA is one of the most promising platforms for accelerating CNN, but the limited bandwidth and on-chip memory size limit the performance of FPGA accelerator for CNN. In this paper, we go deeper with the embedded FPGA platform on accelerating CNNs and propose a CNN accelerator design on embedded FPGA for Image-Net large-scale image classification. We first present an in-depth analysis of state-of-the-art CNN models and show that Convolutional layers are computational-centric and Fully-Connected layers are memory-centric. Then the dynamic-precision data quantization method and a convolver design that is efficient for all layer types in CNN are proposed to improve the bandwidth and resource utilization. Results show that only 0.4% accuracy loss is introduced by our data quantization flow for the very deep VGG16 model when 8/4-bit quantization is used. A data arrangement method is proposed to further ensure a high utilization of the external memory bandwidth. Finally, a state-of-the-art CNN, VGG16-SVD, is implemented on an embedded FPGA platform as a case study. VGG16-SVD is the largest and most accurate network that has been implemented on FPGA end-to-end so far. The system on Xilinx Zynq ZC706 board achieves a frame rate at 4.45 fps with the top-5 accuracy of 86.66% using 16-bit quantization. The average performance of convolutional layers and the full CNN is 187.8 GOP/s and 137.0 GOP/s under 150MHz working frequency, which outperform previous approaches significantly.

1 June 2007 in IEEE Vehicular Technology Magazine
Verified
Journal Article
Closed access
FLFan Li
Fan Li
YWYu Wang
Yu Wang
Vehicular ad hoc network (VANET) is an emerging new technology integrating ad hoc network, wireless LAN (WLAN) and cellular technology to achieve intelligent inter-vehicle communications and improve road traffic safety and efficiency. VANETs are distinguished from other kinds of ad hoc networks by their hybrid network architectures, node movement characteristics, and new application scenarios. Therefore, VANETs pose many unique networking research challenges, and the design of an efficient routing protocol for VANETs is very crucial. In this article, we discuss the research challenge of routing in VANETs and survey recent routing protocols and related mobility models for VANETs.

10 August 2015 in ACM Computing Surveys
Verified
Journal Article
Open access
BGBin Guo
Bin Guo
ZWZhu Wang
Zhu Wang
ZYZhiwen Yu
Zhiwen Yu
YWYu Wang
Yu Wang
NYNeil Y. Yen
Neil Y. Yen
XZXingshe Zhou
Xingshe Zhou
With the surging of smartphone sensing, wireless networking, and mobile social networking techniques, Mobile Crowd Sensing and Computing (MCSC) has become a promising paradigm for cross-space and large-scale sensing. MCSC extends the vision of participatory sensing by leveraging both participatory sensory data from mobile devices (offline) and user-contributed data from mobile social networking services (online). Further, it explores the complementary roles and presents the fusion/collaboration of machine and human intelligence in the crowd sensing and computing processes. This article characterizes the unique features and novel application areas of MCSC and proposes a reference framework for building human-in-the-loop MCSC systems. We further clarify the complementary nature of human and machine intelligence and envision the potential of deep-fused human--machine systems. We conclude by discussing the limitations, open issues, and research opportunities of MCSC.

1 January 2018 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
KGKaiyuan Guo
Kaiyuan Guo
LSLingzhi Sui
Lingzhi Sui
JQJiantao Qiu
Jiantao Qiu
JYJincheng Yu
Jincheng Yu
JWJunbin Wang
Junbin Wang
HYHuazhong Yang
Huazhong Yang
Convolutional neural network (CNN) has become a successful algorithm in the region of artificial intelligence and a strong candidate for many computer vision algorithms. But the computation complexity of CNN is much higher than traditional algorithms. With the help of GPU acceleration, CNN-based applications are widely deployed in servers. However, for embedded platforms, CNN-based solutions are still too complex to be applied. Various dedicated hardware designs on field-programmable gate arrays (FPGAs) have been carried out to accelerate CNNs, while few of them explore the whole design flow for both fast deployment and high power efficiency. In this paper, we investigate state-of-the-art CNN models and CNN-based applications. Requirements on memory, computation and the flexibility of the system are summarized for mapping CNN on embedded FPGAs. Based on these requirements, we propose Angel-Eye, a programmable and flexible CNN accelerator architecture, together with data quantization strategy and compilation tool. Data quantization strategy helps reduce the bit-width down to 8-bit with negligible accuracy loss. The compilation tool maps a certain CNN model efficiently onto hardware. Evaluated on Zynq XC7Z045 platform, Angel-Eye is 6× faster and 5× better in power efficiency than peer FPGA implementation on the same platform. Applications of VGG network, pedestrian detection and face alignment are used to evaluate our design on Zynq XC7Z020. NIVIDA TK1 and TX1 platforms are used for comparison. Angel-Eye achieves similar performance and delivers up to 16× better energy efficiency.

28 March 2019 in ACM Transactions on Reconfigurable Technology and Systems
Verified
Journal Article
Open access
PDF file
KGKaiyuan Guo
Kaiyuan Guo
SZShulin Zeng
Shulin Zeng
JYJincheng Yu
Jincheng Yu
YWYu Wang
Yu Wang
HYHuazhong Yang
Huazhong Yang
Recent research on neural networks has shown a significant advantage in machine learning over traditional algorithms based on handcrafted features and models. Neural networks are now widely adopted in regions like image, speech, and video recognition. But the high computation and storage complexity of neural network inference poses great difficulty on its application. It is difficult for CPU platforms to offer enough computation capacity. GPU platforms are the first choice for neural network processes because of its high computation capacity and easy-to-use development frameworks. However, FPGA-based neural network inference accelerator is becoming a research topic. With specifically designed hardware, FPGA is the next possible solution to surpass GPU in speed and energy efficiency. Various FPGA-based accelerator designs have been proposed with software and hardware optimization techniques to achieve high speed and energy efficiency. In this article, we give an overview of previous work on neural network inference accelerators based on FPGA and summarize the main techniques used. An investigation from software to hardware, from circuit level to system level is carried out to complete analysis of FPGA-based neural network inference accelerator design and serves as a guide to future work.