检索结果-内蒙古大学图书馆

IEEE international conference on Image Processing

作者： Mengjiao Wang Rujie Liu Narishige Abe Hidetsugu Uchida Tomoaki Matsunami Shigefumi Yamada Fujitsu R&D Center Co. LTD Beijing China Fujitsu Laboratories Ltd. Kawasaki Japan

For the sake of better accuracy, the face recognition model is becoming larger and larger, which makes them difficult to be deployed on embedded systems. This work proposes an effective model compression method using knowledge distillation, where a fast student model is trained under the guidance of a complex teacher model. Firstly, different loss combinations and network architectures are analyzed through comprehensive experiments to find the most effective approach. To augment the performance, the feature layer is further normalized to make the optimization objective consistent with cosine similarity metric. Moreover, a teacher weighting strategy is proposed to address the issue when teacher provides wrong guidance. Experimental results show that the student model built by our approach can surpass the teacher model while achieving 3× acceleration.

关键词： Face recognition Computational modeling computer architecture Optimization Degradation Training Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Full-system timing-first simulation 02

Full-system timing-first simulation

引用

Proceedings of the 2002 ACM SIGMETRICS international conference on Measurement and modeling of computer systems

作者： Carl J. Mauer Mark D. Hill David A. Wood University of Wisconsin---Madison

ISBN: (纸本)9781581135312

computer system designers often evaluate future design alternatives with detailed simulators that strive for functional fidelity (to execute relevant workloads) and performance fidelity (to rank design alternatives). Trends toward multi-threaded architectures, more complex micro-architectures, and richer workloads, make authoring detailed simulators increasingly difficult. To manage simulator complexity, this paper advocates decoupled simulator organizations that separate functional and performance concerns. Furthermore, we define an approach, called timing-first simulation, that uses an augmented timing simulator to execute instructions important to performance in conjunction with a functional simulator to insure correctness. This design simplifies software development, leverages existing simulators, and can model micro-architecture timing in *** describe the timing-first organization and our experiences implementing TFsim, a full-system multiprocessor performance simulator. TFsim models a pipelined, out-of-order micro-architecture in detail, was developed in less than one person-year, and performs competitively with previously-published simulators. TFsim's timing simulator implements dynamically common instructions (99.99% of them), while avoiding the vast and exacting implementation efforts necessary to run unmodified commercial operating systems and workloads. Virtutech Simics, a full-system functional simulator, checks and corrects the timing simulator's execution, contributing 18-36% to the overall run-time. TFsim's mostly correct functional implementation introduces a worst-case performance error of 4.8% for our commercial workloads. Some additional simulator performance is gained by verifying functional correctness less often, at the cost of some additional performance error.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Technique of Camera Calibration Based on X-target

A New Technique of Camera Calibration Based on X-target

引用

2010 international conference on Life System modeling and simulation & 2010 international conference on Intelligent Computing for Sustainable Energy and Environment

作者： Ruilin Bai 1, Jingjing Zhao 1, Du Li 1, Wei Meng1 1 Research Institute of Intelligent Control, Jiangnan University, 214122, Wuxi, JiangSu, China

A new technique of camera calibration based on X-target is proposed. Calibration steps include: judging gray saturation, adjusting verticality between optical axis and object surface, two-dimensional plane camera calibration. In the calibration process, the improved Harris operator and spatial moment are used to detect sub-pixel X-target corners, and the accuracy achieves up to 0.1 pixels. It does not need to calculate the specific internal and external camera parameters, and only calculates the relations of world coordinates and image pixel coordinates, and the distortion model. The method has better accuracy and stability, and has been applied in the industrial field of embedded machine vision.

关键词： computer vision, camera calibration, sub-pixel, optical axis verticality

来源：评论

学校读者我要写书评

暂无评论

A high fidelity ATM traffic and network simulator 95

A high fidelity ATM traffic and network simulator

引用

Proceedings of the 27th conference on Winter simulation

作者： Brian W. Unger Fabian Gomes Xiao Zhonge Pawel Gburzynski Theodore Ono-Tesfaye Srinivasan Ramaswamy Carey Williamson Alan Covington Computer Science Department University of Calgary Calgary Alberta T2N 1N4 Canada Computer Science Department University of Alberta Edmonton Alberta T6G 2M7 Computer Science Department University of Saskatchewan Jade Simulations International Calgary Alberta T2N 3P9

ISBN: (纸本)9780780330184

The design of an ATM traffic and network (ATM-TN) simulator which characterizes cell level network behavior is presented. The simulator incorporates three classes of ATM traffic source models: an aggregate ethernet model, an MPEG model and a World Wide Webb transactions model. Six classes of ATM switch architectures are modeled including output buffered, shared memory buffered and cross bar switch models, and then multistage switches which can be built from these three basic models. The ATM-TN simulator can be used to characterize arbitrary ATM networks with dynamic multimedia traffic loads. Call set up and tear down via ATM signaling is implemented in addition to the various types of cell traffic streams generated by voice, video and data. The simulator is built on a simple, efficient simulation language called SimKit which is capable of supporting both fast sequential and parallel execution. Parallel execution is supported using WarpKit, an optimistically synchronized kernel that is aimed at shared memory multiprocessor platforms such as the Silicon Graphics Powerchallenge and Sun Spare 1000 series machines. The paper outlines general requirements for ATM traffic and network simulation, presents an ATM-TN simulator architecture, describes its major components and discusses the major issues associated with cell level ATM modeling and simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modelling of vertical and ferroelectric junctionless technology for efficient 3D neural network compute cube dedicated to embedded artificial intelligence

Modelling of vertical and ferroelectric junctionless technol...

引用

international Electron Devices Meeting (IEDM)

作者： C. Maneux C. Mukherjee M. Deng M. Dubourg L. Reveil G. Bordea A. Lecestre G. Larrieu J. Trommer E.T. Breyer S. Slesazeck T. Mikolajick O. Baumgartner M. Karner D. Pirker Z. Stanojevic David Atienza A. Levisse G. Ansaloni A. Poittevin A. Bosio D. Deleruyelle C. Marchand I. O'Connor IMS University of Bordeaux UMR CNRS 5218 Bordeaux INP Talence France LAAS-CNRS UPR 8001 CNRS Université de Toulouse Toulouse France NaMLab gGmbH Dresden Germany Global TCAD Solutions GmbH Vienna Austria EPFL Lausanne Switzerland INL University of Lyon CNRS UMR 5270 Ecole Centrale de Lyon Ecully France

ISBN: (纸本)9781665425735

This paper presents the set of simulation means used to develop the concept of N 2 C 2 (neural network compute cube) based on a vertical transistor technology platform. On the basis of state-of-the-art junctionless nanowire transistors (JLNT), TCAD simulation, compact modeling and EM simulation are leveraged through a Design-Technology Co-Optimization (DTCO) to achieve innovative 3D circuit architectures. Further, System-Technology Co-Optimization (STCO) implications on 3D NN system architecture are explored.

关键词： Solid modeling Three-dimensional displays Computational modeling systems architecture computer architecture Artificial neural networks Transistors

来源：评论

学校读者我要写书评

暂无评论

A hybrid intelligent system for medical diagnosis

A hybrid intelligent system for medical diagnosis

引用

international Joint conference on Neural Networks (IJCNN)

作者： P. Meesad G.G. Yen School of Electrical and Computer Engineering Intelligent Systems and Control Laboratory Oklahoma State University Stillwater OK USA

ISBN: (纸本)0780370449

We propose a novel hybrid intelligent system (HIS) that is a combination of numerical and linguistic knowledge representation. The proposed HIS is a hierarchical integration of an incremental learning fuzzy neural network (ILFN) and a fuzzy linguistic model optimized via the genetic algorithm. The ILFN is self-organizing network with the capability of fast, online, incremental learning. The linguistic model is constructed based on knowledge embedded in the trained ILFN. The knowledge captured from the low-level ILFN can be mapped to the higher-level linguistic model and vice versa. The GA is applied to optimize the linguistic model to maintain high accuracy and comprehensibility. The resulted HIS is capable of dealing with low-level numerical computation and higher-level linguistic computation. After the system completely constructed, it can incrementally learn new information in both numerical and linguistic structures. To evaluate the system's performance the well-known benchmark Wisconsin breast cancer data was studied as an application to medical diagnosis. The simulation results show that the proposed HIS perform better than the individual standalone systems.

关键词： Hybrid intelligent systems Medical diagnosis Fuzzy neural networks Knowledge representation Genetic algorithms Self-organizing networks System performance Breast cancer Computational modeling Medical simulation

来源：评论

学校读者我要写书评

暂无评论

Alloy surface structure: computer simulations using the BFS method

引用

SURFACE REVIEW AND LETTERS 1997年第5期4卷 825-828页

作者： Bozzolo, G Ferrante, J Analex Corp Brook Pk OH 44142 USA NASA Lewis Res Ctr Cleveland OH 44135 USA

The use of semiempirical methods for modeling ahoy properties has proven to be difficult and limited. The two primary approaches to this modeling, the embedded atom method and the phenomenological method of Miedema, have serious limitations in the range of materials studied and the degree of success in predicting properties of such systems. Recently, a new method has been developed by Bozzolo, Ferrante and Smith (BFS) which has had considerable success in predicting a wide range of alloy properties. In this work, we reference previous BFS applications to surface alloy formation and alloy surface structure, leading to the analysis of binary and ternary Ni-based alloy surfaces. We present Monte Carlo simulation results of thin films of NiAl and Ni-Al-Ti alloys, for a wide range of concentration of the Ti alloying addition. The composition of planes close to the surface as well as bulk features are discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sensor Failure Detection Capabilities in Low-Level Fusion: A Comparison Between Fuzzy Voting and Kalman Filtering

Sensor Failure Detection Capabilities in Low-Level Fusion: A...

引用

2011 IEEE international conference on Robotics and Automation(2011年IEEE世界机器人与自动化大会 ICRA 2011)

作者： Sebastian Blank Thomas Pfister Karsten Berns Department of Computer Sciences Robotics Research LaboratoryKaiserslauternGermany

This paper focuses on the comparison of the low-level sensor failure detection capabilities of model-based Kalman filtering and a model-free Fuzzy voting approach. The ability to identify failing and degrading sensors is essential when dealing with error-prone data acquired in harsh application environments as can be typically found in the field of embedded systems. In order to investigate the respective performance concerning rejection of faulty data several experiments were conducted in a simulation environment. The two candidates were selected to gain more insight into the advantages and limitations of system modeling (or the lack thereof) in signallevel data fusion. The Kalman filter was selected as a typical candidate that relies on extensive models for both the system and information sources. The fuzzy approach, however, employs a heuristic that requires no modeling at all. This results in a broader field of possible applications since detailed knowledge is no longer required. Thus, it can be employed in scenarios that one would not be able to use a model-based algorithm. Such applications include scenarios with ongoing reconfiguration (e. g. wireless sensor networks) or systems with limited detail knowledge about the devices.

关键词： Robot sensing systems Kalman filters Reliability Mathematical model Computational modeling Accuracy Equations

来源：评论

学校读者我要写书评

暂无评论

An FPGA based implementation of a flexible digital PID controller for a motion control system

An FPGA based implementation of a flexible digital PID contr...

引用

international conference on computer Communication and Informatics (ICCCI)

作者： Somsubhra Ghosh Ranjit Kumar Barai Samar Bhattarcharya Prarthana Bhattacharyya Shubhobrata Rudra Arka Dutta Rownick Pyne Department of Electrical Engineering Jadavpur University Kolkata India

ISBN: (纸本)9781467329064

Implementation of digital controllers in embedded environment suffers from the inherent problems associated with analog-digital signals interfacing in hard real-time, therefore, the control algorithms are invariantly subjected to approximations. This paper presents a novel technique for implementation of an efficient FPGA based digital Proportional-Integral-Derivative (PID) controller for the motion control of a permanent magnet DC motor. The implementation technique circumnavigates the problem of interfacing analog and digital systems in real-time. The controller is used in a speed control loop. The hardware implementation has been done on a Xilinx Spartan 3 FPGA chip. A novel technique has been adopted for the generation of the control input as a PWM signal for controlling the motor driver circuit and decoding the optical encoder data for using it for the speed feedback in the PID control loop. The VHDL algorithm for the proposed implementation has also been presented in this paper. A comparison of the experimental results with the Matlab ® based simulation shows the effectiveness of the proposed method.

关键词： Field programmable gate arrays Permanent magnet motors Motion control Pulse width modulation Mathematical model Integrated optics Computational modeling

来源：评论

学校读者我要写书评

暂无评论

modeling Traffic Workloads in Data-center Network simulation Tools

Modeling Traffic Workloads in Data-center Network Simulation...

引用

international conference on High Performance Computing & simulation (HPCS)

作者： Luis Gonzalez-Naharro Jesus Escudero-Sahuquillo Pedro J. García Francisco J. Quiles Jose Duato Wenhao Sun Xiang Yu Hewen Zheng Department of Computing Systems University of Castilla-La Mancha Spain Universitat Politècnica de València Spain Huawei Technologies Co. Ltd. China

ISBN: (数字)9781728144849

ISBN: (纸本)9781728144856

POSTER PAPER Data-centers are commonly used by most important cloud providers worldwide in order to provide storage and computing resources, and, based on these resources, advanced IT services and applications. With the expected explosion of data in the next few years, Data-centers will require new architectures to cope with the new requirements of applications and users. One of the crucial subsystems within the Data-center architecture that must evolve accordingly to the new requirements is the interconnection network or Data-center network (DCN). The DCN performance (basically, high communication bandwidth and low latency) must be guaranteed, otherwise the DCN becoming the system bottleneck. There are several key issues that DCN designers must make decisions on, such as the network topology, routing algorithm, congestion management, etc. An important aspect that impacts on the DCN design are the network communication patterns generated by applications and services. In that sense, an accurate modeling of these traffic workloads would help network designers to make better decisions. In this paper, we present an analysis of the few available studies on traffic modeling for DCNs, in order to gather a set of parameters that define the behaviour of common traffic workloads. Based on these parameters, we have implemented a synthetic DCN traffic generator, which has been included in our simulation framework in order to feed the network with the inferred traffic workloads. We have conducted extensive simulations to test the impact of the parameter variation on the network performance. From the obtained results, we can conclude that the destination distribution is crucial for the network performance. Higher oversubscription of destinations generates incast scenarios that lead to congestion situations and head-of-line blocking, affecting other flows that do not contribute to the incast situation and so spoiling the network performance.

关键词： Facebook computer architecture Bandwidth Analytical models Web servers Load modeling

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：