检索结果-内蒙古大学图书馆

2009 2nd International Congress on Image and Signal Processing, CISP'09

作者： Lei, Wang Xianbin, Wen Xu, Jiao Jianguang, Zhang Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300191 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin 300191 China

ISBN: (纸本)9781424441310

After Mountcastle proposed the theory that all parts of mammalian neocortex are uniform [1], more and more evidences were found to prove that no matter what function the field of neocortex provide, the organizing of cortex cells are same and have an hierarchical structure. It can be inferred every unit of neocortex process information using an identical algorithm. This means if people can find and imitate this algorithm, all intelligence work will be resolved in one way, the only difference is using different sensors. Base on this, Hawkins proposed a top-down model of neocortical operation [2], in which model, both continuous time and prediction play important roles in human's invariant recognition. Then George and Hawkins developed an inspired framework named "Hierarchical Temporal Memory" [3], using a hierarchical Bayesian network to perform prediction and temporal sequence in training the network, which partially implements Hawkins' model, and can provide a rather good performance in invariant recognition. We current study is extending their work by implementing the framework in visual category recognition field. ©2009 IEEE.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Software and hardware co-designed multi-level TLBs for chip multiprocessors

Software and hardware co-designed multi-level TLBs for chip ...

引用

11th IEEE International Conference on Computer and Information technology, CIT 2011 and 11th IEEE International Conference on Scalable computing and Communications, SCALCOM 2011

作者： Zhang, Xiaohui Cong, Ming Chen, Guangqiang Key Laboratory of Computer System and Architecture Institute of Computing Technology Graduate University Beijing China National University of Defense Technology Changsha China

ISBN: (纸本)9780769543888

Translation Lookaside Buffers ( TLBs ) have a significant impact on system performance. Numerous prior studies focus on TLBs design for uniprocessors. With the advent of chip multiprocessors (CMPs), we need a shift to TLBs for chip multiprocessors. This paper presents a software-implemented level-two TLB-SL2-TLB which is a shared level-two TLB for multiprocessors. It not only reduces the cost of TLB refill handler for every processor core, but also reduces the redundant TLB misses' cost for CMPs effectively. Today, CMPs typically employ private per-core TLBs. SL2-TLB together with the hardware TLBs make up a software-hardware co-designed multilevel TLB system which brings great benefit to system performance while avoiding changing the hardware TLB. So it is a convenient and efficient method for CMPs' TLB performance improvement. The benefit brought by SL2-TLB to SPECCPU2000 is less than that to SPECCPU2006, about 5% and 7% separately. Thereinto, the average performance improvement of SPECint 2006 reaches about 12.7%. That is because the overhead for TLB refill is small when the cache is large enough to avoid a miss as walking the page table of applications with small memory footprints. The further optimization for SL2-TLB is kept the SL2-TLB table stay in L2 cache forever by the cache locking scheme. SL2-TLB together with cache locking scheme improves the performances by over 13% for SPECint 2006. And an average performance improvement of over 7% is brought to the new emerging parallel benchmark suite- Princeton Application Repository for Shared-Memory Computers (PARSEC). And all the above evaluations are done on Godson-3 processors which is the latest generation of China's most powerful microprocessor family. © 2011 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Flex memory: Exploiting and managing abundant off-chip optical bandwidth

Flex memory: Exploiting and managing abundant off-chip optic...

引用

作者： Wang, Ying Zhang, Lei Han, Yinhe Li, Huawei Li, Xiaowei Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783981080179

The emerging nanophotonic technology can avoid the limitation of I/O pin count, and provide abundant memory bandwidth. However, current DRAM organization has mainly been optimized for a higher storage capacity and package pin utilization. The resulted data fetching mechanism is quite inefficient in performance and energy saving, and cannot effectively utilize the abundant optical bandwidth in off-chip communication. This paper inspects the opportunity brought by optical communication, and revisits the DRAM memory architecture considering the technology trend towards multiprocessors. In our FlexMemory design, super-line prefetching is proposed to boost system performance and promote energy efficiency, which leverages the abundant photonic bandwidth to enlarge the effective data fetch size per memory cycle. To further preserve locality and maintain service parallelism for different workloads, page folding technique is employed to achieve adaptive data mapping in photonics-connected DRAM chips via optical wavelengths allocation. By combining both techniques, surplus off-chip bandwidth can be utilized and effectively managed adapting to the workloads intensity. Experimental results show that our FlexMemory achieves considerable improvements in performance and energy efficiency. © 2011 EDAA.

关键词： Dynamic random access storage

来源：评论

学校读者我要写书评

暂无评论

Multi‐granularity re‐ranking for visible‐infrared person re‐identification

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 770-779页

作者： Yadi Wang Hongyun Zhang Duoqian Miao Witold Pedrycz Department of Computer Science and Technology Tongji UniversityShanghaiChina Key Laboratory of Embedded System and Service Computing Ministry of EducationShanghaiChina Department of Electrical and Computer Engineering University of AlbertaEdmontonAlbertaCanada System Research Institute Polish Academy of SciencesWarsawPoland

Visible‐infrared person re‐identification(VI‐ReID)is a supplementary task of single‐modality re‐identification,which makes up for the defect of conventional re‐identification under insufficient *** is more challenging than single‐modality ReID because,in addition to difficulties in pedestrian posture,camera shoot-ing angle and background change,there are also difficulties in the cross‐modality *** works only involve coarse‐grained global features in the re‐ranking calculation,which cannot effectively use fine‐grained ***,fine‐grained features are particularly important due to the lack of information in cross‐modality re‐*** this end,the Q‐center Multi‐granularity K‐reciprocal Re‐ranking Algorithm(termed QCMR)is proposed,including a Q‐nearest neighbour centre encoder(termed QNC)and a Multi‐granularity K‐reciprocal Encoder(termed MGK)for a more comprehensive feature *** converts the probe‐corresponding modality features into gallery corresponding modality features through modality transfer to narrow the modality *** takes a coarse‐grained mutual nearest neighbour as the dominant and combines a fine‐grained nearest neighbour as a supplement for similarity *** experiments on two widely used VI‐ReID benchmarks,SYSU‐MM01 and RegDB have shown that our method achieves state‐of‐the‐art ***,the mAP of SYSU‐MM01 is increased by 5.9%in all‐search mode.

关键词： computer vision recognition

来源：评论

学校读者我要写书评

暂无评论

Locality and parallelism optimization for dynamic programming algorithm in bioinformatics

Locality and parallelism optimization for dynamic programmin...

引用

2006 ACM/IEEE Conference on Supercomputing, SC'06

作者： Tan, Guangming Feng, Shengzhong Sun, Ninghui Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences Graduate School Chinese Academy of Sciences

ISBN: (纸本)0769527000

Dynamic programming has been one of the most efficient approaches to sequence analysis and structure prediction in biology. However, their performance is limited due to the drastic increase in both the number of biological data and variety of the computer architectures. With regard to such predicament, this paper creates excellent algorithms aimed at addressing the challenges of improving memory efficiency and network latency tolerance for nonserial polyadic dynamic programming where the dependences are nonuniform. By relaxing the nonuniform dependences, we proposed a new cache oblivious scheme to enhance its performance on memory hierarchy architectures. Moreover we develop and extend a tiling technique to parallelize this nonserial polyadic dynamic programming using an alternate block-cyclic mapping strategy for balancing the computational and memory load, where an analytical parameterized model is formulated to determine the tile volume size that minimizes the total execution time and an algorithmic transformation is used to schedule the tile to overlap communication with computation to further minimize communication overhead on parallel architectures. The numerical experiments were carried out on several high performance computer systems. The new cache-oblivious dynamic programming algorithm achieve 2-10 speedup and the parallel tiling algorithm with communication-computation overlapping shows a desired potential for fine-grained parallel computing on massively parallel computer systems. © 2006 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

On complementary effect of blended behavioral analysis for identity theft detection in mobile social networks 1

引用

13th International Conference on Mobile Ad-hoc and Sensor Networks, MSN 2017

作者： Wang, Cheng Luo, Jing Yang, Bo Jiang, Changjun Key Laboratory of Embedded System and Service Computing Ministry of Education Department of Computer Science and Technology Tongji University Shanghai China

ISBN: (数字)9789811088902

ISBN: (纸本)9789811088896

User behavioral analysis is expected to act as a promising technique for identity theft detection in the Internet. The performance of this paradigm extremely depends on a good individual-level user behavioral model. Such a good model for a specific behavior is often hard to obtain due to the insufficiency of data for this behavior. The insufficiency of specific data is mainly led by the prevalent sparsity of users’ collectable behavioral footprints. This work aims to address whether it is feasible to effectively detect identify thefts by jointly using multiple unreliable behavioral models from sparse individual-level records. We focus on this issue in mobile social networks (MSNs) with multiple dimensions of collectable but sparse data of user behavior, i.e., making check-ins, posing tips and forming friendships. Based on these sparse data, we build user spatial distribution model, user post interest model and user social preference model, respectively. Here, as the arguments, we validate that there is indeed a complementary effect in multi-dimensional blended behavioral analysis for identity theft detection in MSNs. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

High-efficient architecture of Godson-T many-core processor 23

High-efficient architecture of Godson-T many-core processor

引用

23rd IEEE Hot Chips Symposium, HCS 2011

作者： Fan, Dongrui Zhang, Hao Wang, Da Ye, Xiaochun Song, Fenglong Zhang, Junchao Fan, Lingjun Advanced Micro-System Group National Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China

This article consists of a collection of slides from the author's conference presentation on the special features, system design, processing capabilities, and targeted markets for AMS's Godson-T microprocessor...

ISBN: (纸本)9781467388771

关键词：

来源：评论

学校读者我要写书评

暂无评论

Protein structure prediction based on a domain clustering database

Protein structure prediction based on a domain clustering da...

引用

2007 1st International Conference on Bioinformatics and Biomedical Engineering, ICBBE

作者： Ma, Zhaoyun Zhang, Fa Xu, Lin Feng, Shengzhong Liu, Zhiyong Key Laboratory of Computer System and Architecture Chinese Academy of Sciences Institute of Computing Technology Graduate School Chinese Academy of Sciences

ISBN: (纸本)1424411203

Homology modeling, as a successful protein structure prediction method, has two major deficiencies, i.e., the lack of the templates (known structures), and the accuracy of alignment between the query (unknown structure) and its templates. To solve these problems, we have constructed a conservative domain clustering template database, and proposed a profile-based alignment algorithm based on the profile extracted from each domain clustering in the database. The extracted profile can well represent the information of the sequence and structure as well. Compared with other alignment methods, such as T-coffee and Smith-Water man, our results show that with this method it's possible to obtain a higher hit rate for template searching and a more accurate and reliable query-template alignment. Therefore, the quality of protein structure prediction can be improved. © 2007 Crown Copyright.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Towards Stricter Black-box Integrity Verification of Deep Neural Network Models 24

Towards Stricter Black-box Integrity Verification of Deep Ne...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： He, Chaoxiang Bai, Xiaofan Ma, Xiaojing Zhu, Bin B. Hu, Pingyi Fu, Jiayun Jin, Hai Zhang, Dongmei Huazhong University of Science and Technology Hubei Wuhan China Shanghai Jiao Tong University Shanghai China Microsoft Corporation Beijing China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9798400706868

Cloud-based machine learning services offer significant advantages but also introduce the risk of tampering with cloud-deployed deep neural network (DNN) models. Black-box integrity verification (BIV) allows model owners and end-users to determine if a cloud-deployed DNN model has been tampered with by examining only the top-1 label responses. Fingerprinting generates fingerprint samples to query the model, achieving BIV with no impact on the model's accuracy. In this paper, we present BIVBench, the first comprehensive benchmark for BIV of DNN models. BIVBench covers 16 types of model modifications, providing extensive coverage of practical modification scenarios. Our analysis reveals that existing fingerprinting methods, which are typically focused on significant tampering, lack the sensitivity needed to effectively detect subtle yet common and potentially severe modifications. To address this limitation, we propose MiSentry (Model Integrity Sentry), a novel fingerprinting method that leverages meta-learning. MiSentry strategically incorporates a few subtly modified models into the meta-learning model zoo and maximizes the divergence of output predictions between the target model and the modified models in the model zoo to generate highly sensitive, generalizable, and effective fingerprint samples. Extensive evaluations using BIVBench demonstrate that MiSentry outperforms existing state-of-the-art methods overall and significantly surpasses them in detecting subtle modifications. The BIVBench and supplementary materials are available at: https://***/CGCL-codes/BIVBench. © 2024 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

BTMD: A framework of binary translation based malcode detector

BTMD: A framework of binary translation based malcode detect...

引用

4th International Conference on Cyber-Enabled Distributed computing and Knowledge Discovery, CyberC 2012

作者： Shan, Zheng Guo, Haoran Pang, Jianmin Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China National Digital Switching System Engineering and Technology Research Center Zhengzhou China

ISBN: (纸本)9780769548104

Binary Translation technology is used to convert binary code of one Instruction Set Architecture (ISA) into another. This technology can solve the software-inheritance problem and ISA-compatibility between different computers architecture. In this paper, we describe BTMD (Binary Translation based Malcode Detector), a novel framework that exploits static and dynamic binary translation features to detect broad spectrum malware and prevent its execution. By operating directly on binary code with MD Rules on the availability of source code, BTMD is appropriate for translating low-level binary code to high-level proper representation, obtaining CFG (Control Flow Graph) and other high-level Control Structure by MD Parser. Then Critical API Graph based on CFG is generated to do sub graph matching with the defined Malware Behavior Template. MD Engine in BTMD is called to undertake the process to take on the remaining code analysis. Compared with other detection approaches, BTMD is found to be very efficient in terms of detection capability and false alarm rate. © 2012 IEEE.

关键词： Binary codes

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：