422 Hits in 1.8 sec

Recognizing Partial Biometric Patterns [article]

Lingxiao He, Zhenan Sun, Yuhao Zhu, Yunbo Wang
2018 arXiv   pre-print
Zhu is with the Center for Research on Intelligent Perception and Computing (CRIPAC).  ... 
arXiv:1810.07399v1 fatcat:wy3fbzqb4rewngtm4yoclpir3m

Nonparametric Score Estimators [article]

Yuhao Zhou, Jiaxin Shi, Jun Zhu
2020 arXiv   pre-print
., and Zhu, J. A spectral approach to gradient estimation for implicit distributions. In International Conference on Machine Learning, pp. 4651-4660, 2018. Smale, S. and Zhou, D.-X.  ... 
arXiv:2005.10099v2 fatcat:r7h63v3vcvbwfjepymqbfz6fou


Yuhao Zhu, Vijay Janapa Reddi
2014 SIGARCH Computer Architecture News  
Related Work Web browser optimizations Zhu and Reddi propose scheduling to leverage the big/little heterogeneous system for optimizing the energy efficiency of mobile Web browsing [78] .  ... 
doi:10.1145/2678373.2665749 fatcat:7zitexf4qngahppnzppbsa2yeu

Real-Time Spatio-Temporal LiDAR Point Cloud Compression [article]

Yu Feng, Shaoshan Liu, Yuhao Zhu
2020 arXiv   pre-print
Compressing massive LiDAR point clouds in real-time is critical to autonomous machines such as drones and self-driving cars. While most of the recent prior work has focused on compressing individual point cloud frames, this paper proposes a novel system that effectively compresses a sequence of point clouds. The idea to exploit both the spatial and temporal redundancies in a sequence of point cloud frames. We first identify a key frame in a point cloud sequence and spatially encode the key
more » ... by iterative plane fitting. We then exploit the fact that consecutive point clouds have large overlaps in the physical space, and thus spatially encoded data can be (re-)used to encode the temporal stream. Temporal encoding by reusing spatial encoding data not only improves the compression rate, but also avoids redundant computations, which significantly improves the compression speed. Experiments show that our compression system achieves 40x to 90x compression rate, significantly higher than the MPEG's LiDAR point cloud compression standard, while retaining high end-to-end application accuracies. Meanwhile, our compression system has a compression speed that matches the point cloud generation rate by today LiDARs and out-performs existing compression systems, enabling real-time point cloud transmission.
arXiv:2008.06972v1 fatcat:34n3wkil6zad3lduif5vs3cl3u

Assessing the Global Tendency of COVID-19 Outbreak [article]

Qinghe Liu, Zhicheng Liu, Junkai Zhu, Yuhao Zhu, Deqiang Li, Zefei Gao, Liuling Zhou, Junyan Yang, Qiao Wang
2020 medRxiv   pre-print
Wrote the paper: Junkai Zhu, Qinghe Liu, Deqiang Li, Liuling Zhou, Zefei Gao, Zhicheng Liu, and Yuhao Zhu. All authors read and approved the final manuscript.  ...  Analyzed the data: Qinghe Liu, Junkai Zhu, Zhicheng Liu, and Yuhao Zhu. Collect the data: Zefei Gao, and Deqiang Li. Performed the computations: Yuanbo Tang, and Xiang Zhang.  ... 
doi:10.1101/2020.03.18.20038224 fatcat:c4gmxlbimzh2rdztfqvrg5f3t4


Yuhao Zhu, Yangdong Deng, Yubei Chen
2011 Proceedings of the 48th Design Automation Conference on - DAC '11  
With the constantly increasing Internet traffic and fast changing network protocols, future routers have to simultaneously satisfy the requirements for throughput, QoS, flexibility, and scalability. In this work, we propose a novel integrated CPU/GPU microarchitecture, Hermes, for QoS-aware high speed routing. We also develop a new thread scheduling mechanism, which significantly improves all QoS metrics.
doi:10.1145/2024724.2024953 dblp:conf/dac/ZhuDC11 fatcat:rdj7mfj57bhyjgg6vt6qzcshhe

Ptolemy: Architecture Support for Robust Deep Learning [article]

Yiming Gan, Yuxian Qiu, Jingwen Leng, Minyi Guo, Yuhao Zhu
2020 arXiv   pre-print
Deep learning is vulnerable to adversarial attacks, where carefully-crafted input perturbations could mislead a well-trained Deep Neural Network to produce incorrect results. Today's countermeasures to adversarial attacks either do not have capability to detect adversarial samples at inference time, or introduce prohibitively high overhead to be practical at inference time. We propose Ptolemy, an algorithm-architecture co-designed system that detects adversarial attacks at inference time with
more » ... w overhead and high accuracy.We exploit the synergies between DNN inference and imperative program execution: an input to a DNN uniquely activates a set of neurons that contribute significantly to the inference output, analogous to the sequence of basic blocks exercised by an input in a conventional program. Critically, we observe that adversarial samples tend to activate distinctive paths from those of benign inputs. Leveraging this insight, we propose an adversarial sample detection framework, which uses canary paths generated from offline profiling to detect adversarial samples at runtime. The Ptolemy compiler along with the co-designed hardware enable efficient execution by exploiting the unique algorithmic characteristics. Extensive evaluations show that Ptolemy achieves higher or similar adversarial example detection accuracy than today's mechanisms with a much lower runtime (as low as 2%) overhead.
arXiv:2008.09954v1 fatcat:rvsncmxm3bcrhd4f35zjjc3q4q

Graph Neural Network based Agent in Google Research Football [article]

Yizhan Niu, Jinglong Liu, Yuhao Shi, Jiren Zhu
2022 arXiv   pre-print
Deep neural networks (DNN) can approximate value functions or policies for reinforcement learning, which makes the reinforcement learning algorithms more powerful. However, some DNNs, such as convolutional neural networks (CNN), cannot extract enough information or take too long to obtain enough features from the inputs under specific circumstances of reinforcement learning. For example, the input data of Google Research Football, a reinforcement learning environment which trains agents to play
more » ... football, is the small map of players' locations. The information is contained not only in the coordinates of players, but also in the relationships between different players. CNNs can neither extract enough information nor take too long to train. To address this issue, this paper proposes a deep q-learning network (DQN) with a graph neural network (GNN) as its model. The GNN transforms the input data into a graph which better represents the football players' locations so that it extracts more information of the interactions between different players. With two GNNs to approximate its local and target value functions, this DQN allows players to learn from their experience by using value functions to see the prospective value of each intended action. The proposed model demonstrated the power of GNN in the football game by outperforming other DRL models with significantly fewer steps.
arXiv:2204.11142v1 fatcat:ufoqf5u5qzgg7dj2q37r4x7qli

Interactive Summarization and Exploration of Top Aggregate Query Answers [article]

Yuhao Wen, Xiaodan Zhu, Sudeepa Roy, Jun Yang
2018 arXiv   pre-print
Zhu et al. [48] proposed a ranking algorithm with applications in text summarization and social network analysis. Vee et al.  ...  Zhu, A. B. Goldberg, J. V. Gael, and D. Andrzejewski. Improving diversity in ranking using absorbing random walks. In HLT-NAACL, pages 97-104, 2007. [A] = C[A] = * .  ... 
arXiv:1807.11634v1 fatcat:j3h7vo4krbe4hoqbhm2mialaiq

Cloud No Longer a Silver Bullet, Edge to the Rescue [article]

Yuhao Zhu, Gu-Yeon Wei, David Brooks
2018 arXiv   pre-print
This paper takes the position that, while cognitive computing today relies heavily on the cloud, we will soon see a paradigm shift where cognitive computing primarily happens on network edges. The shift toward edge devices is fundamentally propelled both by technological constraints in data centers and wireless network infrastructures, as well as practical considerations such as privacy and safety. The remainder of this paper lays out our view of how these constraints will impact future
more » ... e computing. Bringing cognitive computing to edge devices opens up several new opportunities and challenges, some of which demand new solutions and some of which require us to revisit entrenched techniques in light of new technologies. We close the paper with a call to action for future research.
arXiv:1802.05943v1 fatcat:acugtakfojabba7mc4rlyrcl3q

Research for practice

Peter Bailis, Jean Yang, Vijay Janapa Reddi, Yuhao Zhu
2016 Communications of the ACM  
Second, Vijay Janapa Reddi and Yuhao Zhu provide an overview of the challenges for the future of the mobile Web.  ...  The Red Future of Mobile Web Computing By Vijay Janapa Reddi and Yuhao Zhu The Web is on the cusp of a new evolution, driven by today's most pervasive personal computing platform-mobile devices.  ... 
doi:10.1145/2980989 fatcat:q5gckzwi5jfghfwxxe6v3aqk6m

Crescent: Taming Memory Irregularities for Accelerating Deep Point Cloud Analytics [article]

Yu Feng, Gunnar Hammonds, Yiming Gan, Yuhao Zhu
2022 arXiv   pre-print
3D perception in point clouds is transforming the perception ability of future intelligent machines. Point cloud algorithms, however, are plagued by irregular memory accesses, leading to massive inefficiencies in the memory sub-system, which bottlenecks the overall efficiency. This paper proposes Crescent, an algorithm-hardware co-design system that tames the irregularities in deep point cloud analytics while achieving high accuracy. To that end, we introduce two approximation techniques,
more » ... imate neighbor search and selectively bank conflict elision, that "regularize" the DRAM and SRAM memory accesses. Doing so, however, necessarily introduces accuracy loss, which we mitigate by a new network training procedure that integrates approximation into the network training process. In essence, our training procedure trains models that are conditioned upon a specific approximate setting and, thus, retain a high accuracy. Experiments show that Crescent doubles the performance and halves the energy consumption compared to an optimized baseline accelerator with < 1% accuracy loss. The code of our paper is available at:
arXiv:2204.10707v1 fatcat:ldnrw5vdj5cijf52mpswude3e4

ZhuSuan: A Library for Bayesian Deep Learning [article]

Jiaxin Shi, Jianfei Chen, Jun Zhu, Shengyang Sun, Yucen Luo, Yihong Gu, Yuhao Zhou
2017 arXiv   pre-print
In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural networks and supervised tasks, ZhuSuan is featured for its deep root into Bayesian inference, thus supporting various kinds of probabilistic models, including both the traditional
more » ... archical Bayesian models and recent deep generative models. We use running examples to illustrate the probabilistic programming on ZhuSuan, including Bayesian logistic regression, variational auto-encoders, deep sigmoid belief networks and Bayesian recurrent neural networks.
arXiv:1709.05870v1 fatcat:b2wopv5jgrcitbygcxh6pm7mxq

RTNN: Accelerating Neighbor Search Using Hardware Ray Tracing [article]

Yuhao Zhu
2022 arXiv   pre-print
Yuhao Zhu Background We first define the scope of neighbor search that is considered in this paper (Section 2.1).  ... 
arXiv:2201.01366v2 fatcat:jz4jrywprnhnth5hjzyebzdrqq

Real-Time Gaze Tracking with Event-Driven Eye Segmentation [article]

Yu Feng, Nathan Goulding-Hotta, Asif Khan, Hans Reyserhove, Yuhao Zhu
2022 arXiv   pre-print
Gaze tracking is increasingly becoming an essential component in Augmented and Virtual Reality. Modern gaze tracking al gorithms are heavyweight; they operate at most 5 Hz on mobile processors despite that near-eye cameras comfortably operate at a r eal-time rate (> 30 Hz). This paper presents a real-time eye tracking algorithm that, on average, operates at 30 Hz on a mobile processor, achieves 0.1–0.5 gaze accuracies, all the while requiring only 30K parameters, one to two orders of magn itude
more » ... smaller than state-of-the-art eye tracking algorithms. The crux of our algorithm is an Auto ROI mode, which continuously pr edicts the Regions of Interest (ROIs) of near-eye images and judiciously processes only the ROIs for gaze estimation. To that end, we introduce a novel, lightweight ROI prediction algorithm by emulating an event camera. We discuss how a software emulation of events enables accurate ROI prediction without requiring special hardware. The code of our paper is available at
arXiv:2201.07367v1 fatcat:vu6vn56sx5co3iioste42te6ju
« Previous Showing results 1 — 15 out of 422 results