检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Wang, Jingyuan Feng, Kai Wu, Junjie MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science Engineering Beihang University Beijing100191 China Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations School of Economics and Management Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

The deep network model, with the majority built on neural networks, has been proved to be a powerful framework to represent complex data for high performance machine learning. In recent years, more and more studies turn to nonneural network approaches to build diverse deep structures, and the Deep Stacking Network (DSN) model is one of such approaches that uses stacked easy-to-learn blocks to build a parameter-training-parallelizable deep network. In this paper, we propose a novel SVM-based Deep Stacking Network (SVM-DSN), which uses the DSN architecture to organize linear SVM classifiers for deep learning. A BP-like layer tuning scheme is also proposed to ensure holistic and local optimizations of stacked SVMs simultaneously. Some good math properties of SVM, such as the convex optimization, is introduced into the DSN framework by our model. From a global view, SVM-DSN can iteratively extract data representations layer by layer as a deep neural network but with parallelizability, and from a local view, each stacked SVM can converge to its optimal solution and obtain the support vectors, which compared with neural networks could lead to interesting improvements in anti-saturation and interpretability. Experimental results on both image and text data sets demonstrate the excellent performances of SVM-DSN compared with some competitive benchmark models. Copyright © 2019, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Brief Industry Paper: Towards Efficient Task Scheduling for AUTOSAR using Parallel Pruning

Brief Industry Paper: Towards Efficient Task Scheduling for ...

引用

Real-Time Systems Symposium (RTSS)

作者： Yanxing Yang Nan Zhang Dengke Yan Xian Wei Junlong Zhou Hong Liu Mingsong Chen MoE Engineering Research Center of SW/HW Co-Design Technology and Application East China Normal University School of Computer Science and Engineering Nanjing University of Science and Technology Shanghai Uni-Sentry Intelligent Technology Co. Ltd. China

As a standardized software framework and open E/E system architecture, the AUTomotive Open System ARchitecture (AUTOSAR) has been widely applied to autonomous driving systems to enable real-time control. However, due to the increasing design complexity and the lack of efficient algorithms and design automation tools, it is difficult to quickly figure out an optimal task scheduling scheme for an AUTOSAR-based system. To address this problem, we introduce a novel task scheduling method that can parallelly search for an optimal solution with the help of our proposed pruning strategy. Experimental results on a real-world AUTOSAR-based autonomous driving system demonstrate that our approach can achieve much better task scheduling solutions than the ones obtained manually and significantly reduce the overall task scheduling time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Explainable Recommendation over Knowledge Graphs with Negative Sampling

Reinforcement Learning-Based Explainable Recommendation over...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Siyuan Zhang Yuanxin Ouyang Zhuang Liu Wenge Rong Zhang Xiong State Key Laboratory of Software Development Environment Beihang University Beijing China Engineering Research Center of Advanced Computer Application Technology Ministry of Education Beihang University Beijing China

Introducing knowledge graphs (KGs) into the recommender systems not only improves their performance but also enhances the interpretability. However, most KG-based recommendation methods have the problem of inefficiency and ex-post explanation, which reinforcement learning (RL) methods can solve properly. Most existing RL-based methods for explainable recommendations only consider positive rewards when designing the reward part of the RL environment, which is defective and misleads the policy of the RL agent. To address this problem, we propose Reinforced Knowledge Graph Reasoning with Reinforced Negative Sampling (RKGR-RNS) by introducing a negative sampling method into RL-based recommendation, which refines the reward mechanism to help optimize the agent’s policy. And a judge module is proposed to improve the performance of the recommender system further. Experiments on three real datasets demonstrate that our method is better than the state-of-the-art baseline.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MAKT: Multichannel Attention Networks based Knowledge Tracing with Representation Learning

MAKT: Multichannel Attention Networks based Knowledge Tracin...

引用

IEEE International Conference on Teaching, Assessment and Learning for engineering (TALE)

作者： Xuyang Jiang Yuanxin Ouyang Zhuang Liu Wenge Rong Zhang Xiong State Key Laboratory of Software Development Environment Beihang University Beijing China Engineering Research Center of Advanced Computer Application Technology Ministry of Education Beihang University Beijing China

As an effective and emerging component of intelligent education, Knowledge Tracing(KT) achieves the combination of artificial intelligence and individualized learning, whose aim is to assess students’ mastery of knowledge concepts and assist in developing learning plans. Several existing KT models either use concepts sequence as input and evaluate students’ knowledge state or treat exercise as input to predict students’ future performance. In this paper, we introduce a constraint factor to extract concepts’ and exercises’ relation matrix, design three methods in representation learning, and propose a Multichannel Attention Networks based KT model(MAKT). Specifically, we restrict the co-occurrence relationship within a time window to extract the relation matrix and then train their representations via graph generative learning, graph contrastive learning, and matrix decomposition, respectively. In MAKT, a sliding window is implemented by multichannel where input sequence is sequentially lagged in turn by one position and attention mechanism is applied. We conduct experiments on several benchmark datasets and demonstrate that MAKT with concepts’ and exercises’ representation trained by matrix decomposition outperforms state-of-the-art models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Workflow Scheduling Over Yarn Cluster Using Deep Reinforcement Learning

Towards Efficient Workflow Scheduling Over Yarn Cluster Usin...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Jianguo Xue Ting Wang Puyu Cai MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China Department of Computer Science and Engineering Michigan State University USA

Hadoop Yarn is an open-source cluster manager responsible for resource management and job scheduling. However, data-driven applications are typically organized into workflows that consist of a series of jobs with dependencies. Yarn does not manage users' workflows and only considers the current job rather than the entire workflow when scheduling. In practice, multiple workflows share the same Yarn cluster and are pre-assigned separate Yarn resource queues to avoid mutual interference. However, this coarse-grained resource division can sometimes result in low resource utilization and increased pending time of jobs on the Yarn queue. For instance, one resource queue may have exhausted its quota while still having pending jobs, while other queues may have available resources but cannot begin executing any jobs due to unfulfilled data dependencies. To address this problem, we propose a deep reinforcement learning-based workflow scheduling scheme that takes into account job dependencies, job priorities, and dynamic resource usage. The proposed approach can intelligently identify and utilize free windows of different resource queues. Our simulation results demonstrate that the proposed DRL-based workflow scheduling scheme can significantly reduce the average job latency compared to existing approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

research of Micro-expression Recognition Model based on Feature Unit

Research of Micro-expression Recognition Model based on Feat...

引用

IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C)

作者： Fei Yin Jinyi Xu Yixiang Chen School of Computer Science and Software Engineering East China Normal University Shanghai China MOE Enginering Research Center for Software/Hardware Co-design Technology and Application East China Normal University Shanghai China

ISBN: (数字)9781728189154

ISBN: (纸本)9781728189161

Micro-expression which is the transient expression will be disclosed when people try to hide some kind of real inner emotions. Micro-expression changes so fast that few people detect its existence. As an effective behavioral clue, it is of great significance to understand the change of peoples true feelings. Based on this, image feature extraction in machine learning has made remarkable progress in the past two years. In order to improve the accuracy and practicability of micro-expression recognition, this paper deeply analyzed the practical micro-expression recognition method. Based on landmark detection. We construct a quantitative model and established a machine learning model of micro-expression judgment based on the comprehensive changes of eyes, mouth and eyebrows. This paper combine the feature unit and model application scene for judgement of micro-expression. This method reflect the design idea that the changes of face locality contributed to the overall micro-expression judgment, and helped to complete the high autonomous construction of the micro expression judgment model.

关键词： Face recognition Mouth Machine learning Software quality Software reliability Eyebrows Transient analysis

来源：评论

学校读者我要写书评

暂无评论

AlphaStock: A buying-winners-and-selling-losers investment strategy using interpretable deep reinforcement attention networks

arXiv

引用

arXiv 2019年

作者： Wang, Jingyuan Zhang, Yang Tang, Ke Wu, Junjie Xiong, Zhang MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science Engineering Beihang University Beijing China Institute of Economics School of Social Sciences Tsinghua University Beijing China Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations School of Economics and Management Beihang University Beijing China Beijing Advanced Innovation Center for BDBC Beihang University Beijing China

Recent years have witnessed the successful marriage of finance innovations and AI techniques in various finance applications including quantitative trading (QT). Despite great research efforts devoted to leveraging deep learning (DL) methods for building better QT strategies, existing studies still face serious challenges especially from the side of finance, such as the balance of risk and return, the resistance to extreme loss, and the interpretability of strategies, which limit the application of DL-based strategies in real-life financial markets. In this work, we propose AlphaStock, a novel reinforcement learning (RL) based investment strategy enhanced by interpretable deep attention networks, to address the above challenges. Our main contributions are summarized as follows: i) We integrate deep attention networks with a Sharpe ratio-oriented reinforcement learning framework to achieve a risk-return balanced investment strategy;ii) We suggest modeling interrelationships among assets to avoid selection bias and develop a cross-asset attention mechanism;iii) To our best knowledge, this work is among the first to offer an interpretable investment strategy using deep reinforcement learning models. The experiments on long-periodic U.S. and Chinese markets demonstrate the effectiveness and robustness of AlphaStock over diverse market states. It turns out that AlphaStock tends to select the stocks as winners with high long-term growth, low volatility, high intrinsic value, and being undervalued recently. Copyright © 2019, The Authors. All rights reserved.

关键词： Strategic planning

来源：评论

学校读者我要写书评

暂无评论

Constraining self-interacting dark matter with the full dataset of PandaX-II

引用

Science China(Physics,Mechanics & Astronomy) 2021年第11期64卷 2-7页

作者： Jijun Yang Abdusalam Abdukerim Wei Chen Xun Chen Yunhua Chen Chen Cheng Xiangyi Cui Yingjie Fan Deqing Fang Changbo Fu Mengting Fu Lisheng Geng Karl Giboni Linhui Gu Xuyuan Guo Ke Han Changda He Shengming He Di Huang Yan Huang Ran Huo Yanlin Huang Zhou Huang Xiangdong Ji Yonglin Ju Shuaijie Li Qing Lin Huaxuan Liu Jianglai Liu Xiaoying Lu Wenbo Ma Yugang Ma Yajun Mao Yue Meng Nasir Shaheed Kaixiang Ni Jinhua Ning Xuyang Ning Xiangxiang Ren Changsong Shang Guofang Shen Lin Si Andi Tan Anqing Wang Hongwei Wang Meng Wang QiuHong Wang Siguang Wang Wei Wang Xiuli Wang Zhou Wang Mengmeng Wu Shiyong Wu Weihao Wu Jingkai Xia Mengjiao Xiao Xiang Xiao Pengwei Xie Binbin Yan Yong Yang Chunxu Yu Hai-Bo Yu Jumin Yuan Ying Yuan Xinning Zeng Dan Zhang Tao Zhang Li Zhao Qibin Zheng Jifang Zhou Ning Zhou Xiaopeng Zhou School of Physics and Astronomy Shanghai Jiao Tong UniversityMOE Key Laboratory for Particle Astrophysics and CosmologyShanghai Key Laboratory for Particle Physics and CosmologyShanghai 200240China Shanghai Jiao Tong University Sichuan Research Institude Chengdu 610213China Yalong River Hydropower Development Company Ltd.Chengdu 610051China School of Physics Sun Yat-sen UniversityGaungzhou 510275China Tsung-Dao Lee Institute Shanghai 200240China School of Physics Nankai UniversityTianjin 300071China Key Laboratory of Nuclear Physics and Ion-beam Application(MOE) Institute of Modern PhysicsFudan UniversityShanghai 200433China School of Physics Peking UniversityBeijing 100871China School of Physics Beihang UniversityBeijing 100191China International Research Center for Nuclei and Particles in the Cosmos&Beijing Key Laboratory of Advanced Nuclear Materials and Physics Beihang UniversityBeijing 100191China Shandong Institute of Advanced Technology Jinan 250103China School of Medical Instrument and Food Engineering University of Shanghai for Science and TechnologyShanghai 200093China Department of Physics University of MarylandCollege ParkMaryland 20742USA School of Mechanical Engineering Shanghai Jiao Tong UniversityShanghai 200240China State Key Laboratory of Particle Detection and Electronics University of Science and Technology of ChinaHefei 230026China Department of Modern Physics University of Science and Technology of ChinaHefei 230026China Key Laboratory of Particle Physics and Particle Irradiation of Ministry of Education Shandong UniversityJinan 250100China Research Center for Particle Science and Technology Institute of Frontier and Interdisciplinary ScienceShandong UniversityQingdao 266237China Shanghai Advanced Research Institute Chinese Academy of SciencesShanghai 201210China Department of Physics and Astronomy University of CaliforniaRiversideCalifornia 92507USA Center of High Energy Physics Peking UniversityBeijing 100871China

Self-interacting dark matter(SIDM)is a leading candidate proposed to solve discrepancies between predictions of the prevailing cold dark matter theory and observations of *** SIDM models predict the existence of a light force carrier that mediates strong dark matter *** the mediator couples to the standard model particles,it could produce characteristic signals in dark matter direct detection *** report searches for signals of SIDM models with a light mediator using the full dataset of the PandaX-II experiment,basing on a total exposure of 132 *** significant excess over background is found,and our likelihood analysis leads to a strong upper limit on the dark matter-nucleon coupling *** further combine the PandaX-II constraints and those from observations of the light element abundances in the early universe,and show that direct detection and cosmological probes can provide complementary constraints on dark matter models with a light mediator.

关键词： dark matter direct detection self-interacting dark matter

来源：评论

学校读者我要写书评

暂无评论

Multi-label sparse coding for automatic image annotation

Multi-label sparse coding for automatic image annotation

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Changhu Wang Shuicheng Yan Lei Zhang Hong-Jiang Zhang MOE-MS Key Laboratory of MCC University of Science and Technology China Department of Electrical and Computer Engineering National University of Singapore Singapore Microsoft Research Asia China Microsoft Advanced Technology Center Beijing China

In this paper, we present a multi-label sparse coding framework for feature extraction and classification within the context of automatic image annotation. First, each image is encoded into a so-called supervector, derived from the universal Gaussian Mixture Models on orderless image patches. Then, a label sparse coding based subspace learning algorithm is derived to effectively harness multi-label information for dimensionality reduction. Finally, the sparse coding method for multi-label data is proposed to propagate the multi-labels of the training images to the query image with the sparse ℓ 1 reconstruction coefficients. Extensive image annotation experiments on the Corel5k and Corel30k databases both show the superior performance of the proposed multi-label sparse coding framework over the state-of-the-art algorithms.

关键词： Image coding Image reconstruction Feature extraction Image databases Image retrieval Humans Image segmentation Asia Scattering Image representation

来源：评论

学校读者我要写书评

暂无评论

Cognizant Resource Balancing in Montgomery Modular Multiplication Optimization for Dsp

SSRN

引用

SSRN 2024年

作者： Tao, Qiqi Li, Liying Zhou, Junlong Cao, Guitao Meng, Dan Shanghai Key Laboratory of Trustworthy Computing MoE Engineering Research Center of SW/HW Co-design Technology and Application East China Normal University Shanghai200062 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

The performance of modular multiplication directly influences the efficiency of a majority of encryption ***, there are numerous FPGA-based acceleration techniques targeting modular ***, many of these implementations require substantial hardware resources or suffer from resource ***, we present a novel FPGA-based implementation of Montgomery Modular Multiplication aimed at addressing these *** design employs a suitable radix bit width and word size based on the digital signal processing (DSP) bit width rather than the conventional binary powers of *** aim to instantiate more modular multipliers using limited resources while minimizing *** also introduce a novel DSP cascade structure, called parallel grouping cascade DSP, which reduces the number of clock cycles of internal *** balance the ratio of lookup table (LUT) and DSP usage, we also use multipliers implemented in the LUT to replace some *** results, implemented on Xilinx Virtex-7 field-programmable gate array (FPGA), demonstrate more than 27\% improvement in throughput on 1024-bit modular multiplication and more than 70\% improvement on 2048-bit compared to the best previous state-of-the-art references. © 2024, The Authors. All rights reserved.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：