检索结果-内蒙古大学图书馆

IEEE International conference on Acoustics, Speech and Signal processing

作者： Zhan Gao Elvin Isufi Alejandro Ribeiro Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia USA Department of Intelligent Systems Delft University of Technology Delft The Netherlands

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

Graph neural networks (GNNs) model nonlinear representations in graph data with applications in distributed agent coordination, control, and planning among others. However, current GNN implementations assume ideal distributed scenarios and ignore link fluctuations that occur due to environment or human factors. In these situations, the GNN fails to address its distributed task if the topological randomness is not considered accordingly. To overcome this issue, we put forth the stochastic graph neural network (SGNN) model: a GNN where the distributed graph convolutional operator is modified to account for the network changes. Since stochasticity brings in a new paradigm, we develop a novel learning process for the SGNN and introduce the stochastic gradient descent (SGD) algorithm to estimate the parameters. We prove through the SGD that the SGNN learning process converges to a stationary point under mild Lipschitz assumptions. Numerical simulations corroborate the proposed theory and show an improved performance of the SGNN compared with the conventional GNN when operating over random time varying graphs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeepHash: An End-to-End Learning Approach for Metadata Management in distributed File Systems 19

DeepHash: An End-to-End Learning Approach for Metadata Manag...

引用

48th International conference on Parallel processing (ICPP)

作者： Gao, Yuanning Gao, Xiaofeng Chen, Guihai Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai Key Lab Scalable Comp & Syst Shanghai Peoples R China

ISBN: (纸本)9781450362955

In distributed file systems, distributed metadata management can be considered as a mapping problem, i.e., how to effectively map the metadata namespace tree to multiple metadata servers (MDS's). In general, all traditional distributed metadata management schemes simply presume a rigid mapping function, thus failing to adaptively meet the requirements of different applications. To better take advantage of the current distribution of the metadata, in this exploratory paper, we present the first machine learning based model called DeepHash, which leverages the deep neural network to learn a locality preserving hashing (LPH) mapping. To help learn a good position relationship of metadata nodes in the namespace tree, we first present a metadata representation strategy. Due to the absence of training labels, i.e., the hash values of metadata nodes, we design two kinds of loss functions with distinctive characters to train DeepHash respectively, including a pair loss and a triplet loss, and introduce some sampling strategies for these two approaches. We conduct extensive experiments on Amazon EC2 platform to compare the performance of DeepHash with traditional and state-of-the-art schemes. The results demonstrate that DeepHash can preserve the metadata locality well while maintaining a high load balancing, which denotes the effectiveness and efficiency of DeepHash.

关键词： metadata management neural network locality preserving hashing distributed file system

来源：评论

学校读者我要写书评

暂无评论

Power Quality Enhancement in AC Microgrids Using Integrated Genetic Algorithm in ANN

Power Quality Enhancement in AC Microgrids Using Integrated ...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： M. Vijay Karthik Priyanka Chaudhary Noida International University Greater Noida India

ISBN: (纸本)9781665435253

This article presents the detailed analysis of power quality improvement in microgrids by using the multiple schemes. The microgrid contains the various renewable energy sources, and they are interconnected with the power electronic converters. These converters are faced the many issues with respect to the reactive inrush currents and harmonic voltages. These currents also resulted in voltage drop across the line impedances. The voltage harmonics and fluctuations can generate the malfunctioning, overheating and equipment tripping issues. The microgrid stability mainly depends upon the optimization method and compensation of various micro grid units. This article mainly focused on development of smart grid system by combining the two individual microgrids using electronically coupled distributed energy resources (EC-DER) inverter and smart impedance (SI) converter. Thus, the optimal power flow was achieved based on the each individual microgrid available power. The two “parallel optimization” methods are used to optimize various power quality challenges such as operation mode transfer transients, harmonic load sharing and parallel control of current and voltage quality. Thus, artificial neural network (ANN) approach is used for improving EC-DER performance and genetic algorithm (GA) is used for improving SI performance. The stability of the system is achieved by operating the ANN-GA in parallel processing manner. Thus, two microgrids develops the individual powers and optimal power flow is generated in smart grid. The simulation results shows that the proposed ANN-GA controller results the reduced total harmonic distortion (THD) and fault setting time in microgrids as compared to the conventional model predictive control (MPC) approach.

关键词： Power quality Microgrids Artificial neural networks Power system stability Parallel processing Harmonic analysis Stability analysis

来源：评论

学校读者我要写书评

暂无评论

A Supervised Method for Extractive Single Document Summarization Based on Sentence Embeddings and neural networks 1

引用

2nd International conference on Advanced Intelligent Systems for Sustainable Development, AI2SD 2019

作者： Lamsiyah, Salima El Mahdaouy, Abdelkader El Alaoui, Said Ouatik Espinasse, Bernard Laboratory of Informatics and Modeling FSDM Sidi Mohamed Ben Abdellah University Fez Morocco LIS UMR CNRS 7020 Aix-Marseille Université/Université de Toulon Marseille France

ISBN: (数字)9783030366742

ISBN: (纸本)9783030366735

Extractive summarization consists of generating a summary by ranking sentences from the original texts according to their importance and salience. Text representation is a fundamental process that affects the effectiveness of many text summarization methods. distributed word vector representations have been shown to improve Natural Language processing (NLP) tasks, especially Automatic Text Summarization (ATS). However, most of them do not consider the order and the context of the words in a sentence. This does not fully allow grasping the sentence semantics and the syntactic relationships between sentences constituents. In this paper, to overcome this problem, we propose a deep neural network model based-method for extractive single document summarization using the state-of-the-art sentence embedding models. Experiments are performed on the standard DUC2002 dataset using three sentence embedding models. The obtained results show the effectiveness of the used sentence embedding models for ATS. The overall comparison results show that our method outperforms eight well-known ATS baselines and achieves comparable results to the state-of-the-art deep learning based methods. © 2020, Springer Nature Switzerland AG.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Spiking Neurons, the Natural Key to Exploit Temporal Sparsity

引用

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS 2019年第4期9卷 668-678页

作者： Yousefzadeh, Amirreza Khoei, Mina A. Hoseini, Sahar Holanda, Priscila Leroux, Sam Moreira, Orlando Tapson, Jonathan Dhoedt, Bart Simoens, Pieter Serrano-Gotarredona, Teresa Linares-Barranco, Bernabe GML NL-5656 AG Eindhoven Netherlands GML F-75012 Paris France Univ Seville CSIC Inst Microelect Seville Seville 41004 Spain Univ Ghent IMEC IDLab B-9052 Ghent Belgium GML San Jose CA 94043 USA

Inference of Deep neural networks for stream signal (Video/Audio) processing in edge devices is still challenging. Unlike the most state of the art inference engines which are efficient for static signals, our brain is optimized for real-time dynamic signal processing. We believe one important feature of the brain (asynchronous state-full processing) is the key to its excellence in this domain. In this work, we show how asynchronous processing with state-full neurons allows exploitation of the existing sparsity in natural signals. This paper explains three different types of sparsity and proposes an inference algorithm which exploits all types of sparsities in the execution of already trained networks. Our experiments in three different applications (Handwritten digit recognition, Autonomous Steering and Hand-Gesture recognition) show that this model of inference reduces the number of required operations for sparse input data by a factor of one to two orders of magnitudes. Additionally, due to fully asynchronous processing this type of inference can be run on fully distributed and scalable neuromorphic hardware platforms.

关键词： neural networks Artificial neural networks Inference algorithms Algorithm design and analysis Asynchronous communication Spiking neural network (SNN) Asynchronous Inference Temporal sparsity Deep neural network Convolutional neural network (CNN) Bio-inspired processing Neuromorphic Hardware

来源：评论

学校读者我要写书评

暂无评论

Security for distributed Deep neural networks: Towards Data Confidentiality & Intellectual Property Protection 16

Security for Distributed Deep Neural Networks: Towards Data ...

引用

16th International Joint conference on E-Business and Telecommunications (ICETE)

作者： Gomez, Laurent Wilhelm, Marcus Marquez, Jose Duverger, Patrick SAP Global Secur SAP Secur Res Toulouse France Univ Potsdam Hasso Plattner Inst Potsdam Germany SAP SE SAP Portfolio Strategy & Technol Adopt Bonn Germany Logist & IT Serv City Antibes Juan Pins France

ISBN: (纸本)9789897583780

Current developments in Enterprise Systems observe a paradigm shift, moving the needle from the backend to the edge sectors of those;by distributing data, decentralizing applications and integrating novel components seamlessly to the central systems. Distributively deployed AI capabilities will thrust this transition. Several non-functional requirements arise along with these developments, security being at the center of the discussions. Bearing those requirements in mind, hereby we propose an approach to holistically protect distributed Deep neural network (DNN) based/enhanced software assets, i.e. confidentiality of their input & output data streams as well as safeguarding their Intellectual Property. Making use of Fully Homomorphic Encryption (FHE), our approach enables the protection of distributed neural networks, while processing encrypted data. On that respect we evaluate the feasibility of this solution on a Convolutional Neuronal network (CNN) for image classification deployed on distributed infrastructures.

关键词： distributed Systems neural networks Intellectual Property Data Protection & Privacy Fully Homomorphic Encryption

来源：评论

学校读者我要写书评

暂无评论

Surrogate Supervision-based Deep Weakly-supervised Anomaly Detection

Surrogate Supervision-based Deep Weakly-supervised Anomaly D...

引用

IEEE International conference on Data Mining Workshops (ICDM Workshops)

作者： Zhiyue Wu Hongzuo Xu Yijie Wang Yongjun Wang Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha China

ISBN: (纸本)9781665424288

Many anomaly detection applications can provide partially observed anomalies, but only limited work is for this setting. Additionally, a number of anomaly detectors focus on learning a particular model of normal/abnormal class. However, the intra-class model might be too complicated to be accurately learned. It is still a non-trivial task to handle data with anomalies/inliers in skewed and heterogeneous distributions. To address these problems, this paper proposes an anomaly detection method to leverage Partially Labeled anomalies via Surrogate supervision-based Deviation learning (denominated PLSD). The original supervision (i.e., known anomalies and a set of explored inliers) is transferred to semantic-rich surrogate supervision signals (i.e., anomaly-inlier and inlier-inlier class) via vector concatenation. Then different relationships and interactions between anomalies and inliers are directly and efficiently learned thanks to the neural network’s connection property. Anomaly scoring is processed via the trained network and the high-efficacy inliers. Extensive experiments show that PLSD significantly prevails state-of-the-art semi/weakly-supervised anomaly detectors.

关键词： Learning systems conferences Detectors Gaussian distribution Benchmark testing Task analysis Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Framework for distributed Deep neural network Training with Heterogeneous Computing Platforms 25

A Framework for Distributed Deep Neural Network Training wit...

引用

25th IEEE International conference on Parallel and distributed Systems (IEEE ICPADS)

作者： Gu, Bontak Kong, Joonho Munir, Arslan Kim, Young Geun Kyungpook Natl Univ Sch Elect Engn Daegu South Korea Kansas State Univ Dept Comp Sci Manhattan KS 66506 USA Korea Univ Dept Comp Sci Seoul South Korea

ISBN: (纸本)9781728125831

Deep neural network (DNN) training is generally performed by cloud computing platforms. However, cloud-based training has several problems such as network bottleneck, server management cost, and privacy. To overcome these problems, one of the most promising solutions is distributed DNN model training which trains the model with not only high-performance servers but also low-end power-efficient mobile edge or user devices. However, due to the lack of a framework which can provide an optimal cluster configuration (i.e., determining which computing devices participate in DNN training tasks), it is difficult to perform efficient DNN model training considering DNN service providers' preferences such as training time or energy efficiency. In this paper, we introduce a novel framework for distributed DNN training that determines the best training cluster configuration with available heterogeneous computing resources. Our proposed framework utilizes pre-training with a small number of training steps and estimates training time, power, energy, and energy-delay product (EDP) for each possible training cluster configuration. Based on the estimated metrics, our framework performs DNN training for the remaining steps with the chosen best cluster configurations depending on DNN service providers' preferences. Our framework is implemented in TensorFlow and evaluated with three heterogeneous computing platforms and five widely used DNN models. According to our experimental results, in 76.67% of the cases, our framework chooses the best cluster configuration depending on DNN service providers' preferences with only a small training time overhead.

关键词： distributed processing Deep neural network Training time Energy efficiency Edge Computing

来源：评论

学校读者我要写书评

暂无评论

Single High-Value Region Detection Based on Image Equal-Segmentation 12

Single High-Value Region Detection Based on Image Equal-Segm...

引用

12th International conference on Cyber-Enabled distributed Computing and Knowledge Discovery, CyberC 2020

作者： Chen, Jinlong Huang, Lei Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China School of Computer Information and Security Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9781728184487

With the development of computer hardware equipment and deep neural network (DNN) technology, computer vision has received more and more attention from AI developers and researchers. In the field of digital image processing, people try to use some calculation methods and techniques to identify objects in images. In the process of finding the rules, this method is called target detection, which is also a research hotspot in the field of computer vision. High-value area detection is based on target detection technology. On the basis of image detection of digital images, some methods of image are used to segment more concerned areas in the target. In this paper, the method of equally segmenting the image takes the image containing the detected object as input and performs detection to achieve the purpose of detecting high-value areas. The steps of the algorithm are divided into high-value area estimation, image equal segmentation, image data attenuation, algorithm acceleration, target fusion and classification. (Abstract) © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Robustly Executing DNNs in IoT Systems Using Coded distributed Computing 19

Robustly Executing DNNs in IoT Systems Using Coded Distribut...

引用

56th ACM/EDAC/IEEE Design Automation conference (DAC)

作者： Hadidi, Ramyad Cao, Jiashen Ryoo, Michael S. Kim, Hyesoon Georgia Tech Atlanta GA 30332 USA Google Brain Mountain View CA USA

ISBN: (纸本)9781450367257

Internet of Things ( IoT) devices have access to an abundance of raw data for processing. With deep neural networks ( DNNs), not only the demand for the computing power of IoT devices is increasing, but also privacy concerns are motivating the importance of close-to-edge computation. DNN execution by distributing its computation is common in IoT systems. However, managing unstable latencies in a network and intermittent failures are serious challenges. Our work provides robustness and close-to-zero recovery latency by adapting coded distributed computing ( CDC). We analyze robust execution on a mesh of Raspberry Pis by studying four DNNs.

关键词： Deep neural networks

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：