检索结果-内蒙古大学图书馆

Convergence Analysis of an SLF-NMU Algorithm for Non-negative Latent Factor Analysis on a High-Dimensional and Sparse Matrix

学校读者我要写书评

暂无评论

Convergence Analysis of an SLF-NMU Algorithm for Non-negativ...

IEEE International Conference on Systems, Man and Cybernetics

作者： Zhigang Liu Xin Luo Chongqing Engineering Research Center of Big Data Application for Smart Cities and Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

Non-negative latent factor (NLF) models have been frequently applied to information extraction, pattern recognition, and community detection. An NLF model can well represent a high-dimensional and sparse (HiDS) matrix of non-negative data and efficiently acquire useful knowledge from it. A single latent factor-dependent, non-negative and multiplicative update (SLF-NMU) algorithm is highly efficient to build NLF model. However, its convergence ability on such a matrix is still unveiled in theory. This paper presents the convergence property of an SLF-NMU algorithm. We theoretically prove that it can guarantee its convergence to a Karush-Kuhn-Tucher (KKT) stationary point. Empirical studies on two HiDS matrices from practical applications indicate that an SLF-NMU algorithm make an NLF model to converge at a relatively steady state.

关键词： Sparse matrices Convergence Computational modeling Analytical models Linear programming data models Technological innovation

Supervised deep semantics-preserving hashing for real-time pulmonary nodule image retrieval

学校读者我要写书评

暂无评论

Supervised deep semantics-preserving hashing for real-time p...

作者： Qi, Yongjun Gu, Junhua Zhang, Yajuan Wu, Gengshen Wang, Feng State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology Tianjin China Laboratory of Electromagnetic Field and Electrical Apparatus Reliability Hebei University of Technology Tianjin China Information Technology Center North China Institute of Aerospace Engineering Langfang China School of Artificial Intelligence Hebei University of Technology Tianjin China School of Computing and Communications Lancaster University Lancaster United Kingdom Hebei Province Key Laboratory of Big Data Calculation Hebei University of Technology Tianjin China

Hashing-based medical image retrieval has drawn extensive attention recently, which aims at providing effective aided diagnosis for medical personnel. In the paper, a novel deep hashing framework is proposed in the medical image retrieval, where the processes of deep feature extraction, binary code learning, and deep hash function learning are jointly carried out in supervised fashion. Particularly, the discrete constrained objective function in the hash code learning is optimized iteratively, where the binary code can be directly solved with no need for relaxation. In the meantime, the semantic similarity is maintained by fully exploring supervision information during the discrete optimization, where the neighborhood structure of training data is preserved by applying a graph regularization term. Additionally, to gain the fine-grained ranking of the returned medical images sharing the same Hamming distance, a novel image re-ranking scheme is proposed to refine the similarity measurement by jointly considering Euclidean distance between the real-valued feature descriptors and their category information between those images. Extensive experiments on the pulmonary nodule image dataset demonstrate that the proposed method can achieve better retrieval performance over the state of the arts. © 2020, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Semantics

A Nonlinear Proportional Integral Derivative-Incorporated Stochastic Gradient Descent-based Latent Factor Model

学校读者我要写书评

暂无评论

A Nonlinear Proportional Integral Derivative-Incorporated St...

IEEE International Conference on Systems, Man and Cybernetics

作者： Jinli Li Ye Yuan Computer School China West Normal University Nanchong China Chongqing Institute of Green and Intelligent Technology Chongqing China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728185262

ISBN: (纸本)9781728185279

Recommender system (RS) commonly describes its user-item preferences with a high-dimensional and sparse (HiDS) matrix. A latent factor (LF) model relying on stochastic gradient descent (SGD) is frequently adopted to extract useful information from such an HiDS matrix. In spite of its efficiency, an SGD-based LF model commonly takes many iterations to converge. When processing a large-scale HiDS matrix, its computational efficiency should be further improved by further accelerating its convergence rate as well as maintaining its learning ability. To address this issue, this paper innovatively proposes novel SGD algorithm which incorporates a nonlinear proportional integral derivative (NPID) controller into its learning scheme for building an LF model. The main idea is to adopt an NPID controller to model the learning residual achieved in the past iterations, thereby adjusting the learning direction and step size of the current iteration, thereby making a resultant model converge fast. With the NPID-incorporated SGD algorithm, this study proposes an NPID-SGD-based LF (NSLF) model. Experimental results on two HiDS matrices demonstrate that compared with a standard SGD-based LF model, the proposed model achieves higher computational efficiency and prediction accuracy for missing data of an HiDS matrix.

关键词： Computational modeling Stochastic processes Predictive models data models Computational efficiency Sparse matrices Convergence

FAIR1M: A benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sun, Xian Wang, Peijin Yan, Zhiyuan Wang, Cheng Diao, Wenhui Chen, Jin Li, Jihao Feng, Yingchao Xu, Tao Weinmann, Martin Hinz, Stefan Fu, Kun Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China Fujian Key Laboratory of Sensing and Computing for Smart Cities School of Information Science and Engineering Xiamen University Xiamen361005 China Fujian Collaborative Innovation Center for Big Data Applications in Governments Fuzhou350003 China Beijing Remote Sensing Information Institute Beijing100011 China Institute of Photogrammetry and Remote Sensing Karlsruhe Institute of Technology Karlsruhe Germany

With the rapid development of deep learning, many deep learning based approaches have made great achievements in object detection task. It is generally known that deep learning is a data-driven method. data directly impact the performance of object detectors to some extent. Although existing datasets have included common objects in remote sensing images, they still have some limitations in terms of scale, categories, and images. Therefore, there is a strong requirement for establishing a large-scale benchmark on object detection in high-resolution remote sensing images. In this paper, we propose a novel benchmark dataset with more than 1 million instances and more than 15,000 images for Fine-grAined object recognItion in high-Resolution remote sensing imagery which is named as FAIR1M. We collected remote sensing images with a resolution of 0.3m to 0.8m from different platforms, which are spread across many countries and regions. All objects in the FAIR1M dataset are annotated with respect to 5 categories and 37 sub-categories by oriented bounding boxes. Compared with existing detection datasets dedicated to object detection, the FAIR1M dataset has 4 particular characteristics: (1) it is much larger than other existing object detection datasets both in terms of the quantity of instances and the quantity of images, (2) it provides more rich fine-grained category information for objects in remote sensing images, (3) it contains geographic information such as latitude, longitude and resolution, (4) it provides better image quality owing to a careful data cleaning procedure. To establish a baseline for fine-grained object recognition, we propose a novel evaluation method and benchmark fine-grained object detection tasks and a visual classification task using several State-Of-The-Art (SOTA) deep learning based models on our FAIR1M dataset. Experimental results strongly indicate that the FAIR1M dataset is closer to practical application and it is considerably more challeng

关键词： Object recognition

Advanced Spin Orbit Torque Magnetic Random Access Memory with Field-Free Switching Schemes (Invited)

学校读者我要写书评

暂无评论

Advanced Spin Orbit Torque Magnetic Random Access Memory wit...

International Conference on Solid-State and Integrated Circuit Technology

作者： Chao Wang Zhaohao Wang Shouzhong Peng Youguang Zhang Weisheng Zhao Fert Beijing Research Institute Beihang University Beijing China School of Electronics and Information Engineering Beihang University Beijing China School of Microelectronics Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (数字)9781728162355

ISBN: (纸本)9781728162362

Magnetic random access memory (MRAM) is considered a promising candidate for future both standalone and embedded memory technology. The emerging spin orbit torque (SOT) mechanism is expected to alternate the traditional spin transfer torque (STT) writing scheme. However, the need of undesirable magnetic field limits the application of SOT mechanism. In this invited paper, we outline our latest achievements on the field-free SOT-MRAM. First, we proposed a toggle spin torque MRAM (TST-MRAM) by combining STT and SOT. Second, we experimentally demonstrated a voltage-gated SOT mechanism assisted by voltage-controlled magnetic anisotropy (VCMA) and in-plane exchange bias (EB). Finally, we presented a current-path-dependent SOT mechanism aided by uniaxial shape anisotropy.

关键词： Magnetization Magnetic tunneling Torque Strips Spintronics Optical switches Logic gates

DP Compress: a Model Compression Scheme for Generating Efficient Deep Potential Models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lu, Denghui Jiang, Wanrun Chen, Yixiao Zhang, Linfeng Jia, Weile Wang, Han Chen, Mohan HEDPS CAPT College of Engineering Peking University Beijing100871 China Songshan Lake Materials Laboratory Guangdong Dongguan523808 China Institute of Physics Chinese Academy of Sciences Beijing100190 China Program in Applied and Computational Mathematics Princeton University PrincetonNJ United States Beijing Institute of Big Data Research Beijing100871 China Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Laboratory of Computational Physics Institute of Applied Physics and Computational Mathematics Fenghao East Road 2 Beijing100094 China

Machine-learning-based interatomic potential energy surface (PES) models are revolutionizing the field of molecular modeling. However, although much faster than electronic structure schemes, these models suffer from costly computations via deep neural networks to predict the energy and atomic forces, resulting in lower running efficiency as compared to the typical empirical force fields. Herein, we report a model compression scheme for boosting the performance of the Deep Potential (DP) model, a deep learning based PES model. This scheme, we call DP Compress, is an efficient post-processing step after the training of DP models (DP Train). DP Compress combines several DP-specific compression techniques, which typically speed up DP-based molecular dynamics simulations by an order of magnitude faster, and consume an order of magnitude less memory. We demonstrate that DP Compress is sufficiently accurate by testing a variety of physical properties of Cu, H2O, and Al-Cu-Mg systems. DP Compress applies to both CPU and GPU machines and is publicly available online. Copyright © 2021, The Authors. All rights reserved.

关键词： Molecular dynamics

Beyond triplet loss: Person re-identification with fine-grained difference-aware pairwise loss

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yan, Cheng Pang, Guansong Bai, Xiao Zhou, Jun Gu, Lin School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China School of Computer Science University of Adelaide Austria School of Information and Communication Technology Griffith University Australia National Institute of Informatics University of Tokyo Japan

Person Re-IDentification (ReID) aims at re-identifying persons from different viewpoints across multiple cameras. Capturing the fine-grained appearance differences is often the key to accurate person ReID, because many identities can be differentiated only when looking into these fine-grained differences. However, most state-of-the-art person ReID approaches, typically driven by a triplet loss, fail to effectively learn the fine-grained features as they are focused more on differentiating large appearance differences. To address this issue, we introduce a novel pairwise loss function that enables ReID models to learn the fine-grained features by adaptively enforcing an exponential penalization on the images of small differences and a bounded penalization on the images of large differences. The proposed loss is generic and can be used as a plugin to replace the triplet loss to significantly enhance different types of state-of-the-art approaches. Experimental results on four benchmark datasets show that the proposed loss substantially outperforms a number of popular loss functions by large margins;and it also enables significantly improved data efficiency. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

Field-free Deterministic Magnetization Switching Induced by Interlaced Spin-Orbit Torques

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Min Wang, Zhaohao Wang, Chao Zhao, Weisheng Fert Beijing Research Institute Beihang University Beijing China School of Microelectronics Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Electronics and Information Engineering Beihang University Beijing China

Spin-orbit torque (SOT) based magnetic random access memory (MRAM) is envisioned as an emerging non-volatile memory due to its ultra-high speed and low power consumption. The field-free switching schema in SOT devices is of great interest to both academia and industry. Here we propose a novel field-free deterministic magnetization switching in a regular magnetic tunnel junction (MTJ) by using two currents sequentially passing interlaced paths, with less requirements of manufacturing process or additional physical effects. The switching is bipolar since the final magnetization state depends on the combination of current paths. The functionality and robustness of the proposed schema is validated through both macrospin and micromagnetic simulation. The influences of field-like torque and Dzyaloshinskii-Moriya interaction (DMI) effect are further researched. Our proposed schema shows good scalability and is expected to realize novel digital logic and even computing-in-memory platform. Copyright © 2020, The Authors. All rights reserved.

关键词： Torque

TCIM: Triangle counting acceleration with processing-in-MRAM architecture

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Xueyan Yang, Jianlei Zhao, Yinglin Qi, Yingjie Liu, Meichen Cheng, Xingzhou Jia, Xiaotao Chen, Xiaoming Qu, Gang Zhao, Weisheng Fert Beijing Research Institute School of Microelectronics Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering University of Maryland College ParkMD United States

Triangle counting (TC) is a fundamental problem in graph analysis and has found numerous applications, which motivates many TC acceleration solutions in the traditional computing platforms like GPU and FPGA. However, these approaches suffer from the bandwidth bottleneck because TC calculation involves a large amount of data transfers. In this paper, we propose to overcome this challenge by designing a TC accelerator utilizing the emerging processing-in-MRAM (PIM) architecture. The true innovation behind our approach is a novel method to perform TC with bitwise logic operations (such as AND), instead of the traditional approaches such as matrix computations. This enables the efficient in-memory implementations of TC computation, which we demonstrate in this paper with computational Spin-Transfer Torque Magnetic RAM (STT-MRAM) arrays. Furthermore, we develop customized graph slicing and mapping techniques to speed up the computation and reduce the energy consumption. We use a device-to-architecture co-simulation framework to validate our proposed TC accelerator. The results show that our data mapping strategy could reduce 99.99% of the computation and 72% of the memory WRITE operations. Compared with the existing GPU or FPGA accelerators, our in-memory accelerator achieves speedups of 9× and 23.4×, respectively, and a 20.6× energy efficiency improvement over the FPGA accelerator. Copyright © 2020, The Authors. All rights reserved.

关键词： data transfer