The Partitioned Global Address Space (PGAS) model has been widely used in multi-core clusters as an alternative to MPI. Among the widespread use is Unified Parallel C (UPC). Previous research has shown that UPC perfor...
详细信息
ISBN:
(纸本)9781479909735
The Partitioned Global Address Space (PGAS) model has been widely used in multi-core clusters as an alternative to MPI. Among the widespread use is Unified Parallel C (UPC). Previous research has shown that UPC performance is comparable with MPI, however in certain cases UPC require hand-tuning techniques such as pre-fetching and privatized pointers-to-shared to improve the performance. In this paper we reviews, evaluate and analyze the performance pattern between UPC Naive, UPC optimize and MPI on two different multi-core clusters architecture. We focus our study using matrix multiplication as the benchmark and perform our experimental on two distributed memory machine;Cray XE6 with Gemini interconnects and Sun Cluster with Infiniband interconnects. We provide analysis on each core execution time to understand the pattern of communication for both machines. We also demonstrate the gaps between naive and optimized are depends on the compiler with its associate distributed memory machine. We also observed unnecessary optimization for certain programs related to HPC architecture and compiler.
Learning the signal statistics and calibration are essential procedures for supervised machine learning algorithms. For some applications, e. g ERP based brain computer interfaces, it might be important to reduce the ...
详细信息
ISBN:
(纸本)9781467310260
Learning the signal statistics and calibration are essential procedures for supervised machine learning algorithms. For some applications, e. g ERP based brain computer interfaces, it might be important to reduce the duration of the calibration, especially for the ones requiring frequent training of the classifiers. However simply decreasing the number of calibration samples would decrease the performance of the algorithm if the algorithm suffers from curse of dimensionality or low signal to noise ratio. As a remedy, we propose estimating the performance of the algorithm during the calibration in an online manner, which would allow us to terminate the calibration session if required. Consequently, early termination means a reduction in time spent. In this paper, we present an updating algorithm for regularized discriminant analysis (RDA) to modify the classifier using the new supervised data collected. The proposed procedure considerably reduces the time required for updating the RDA classifiers compared to recalibrating them, that would make the performance estimation applicable in real time.
This article focuses on remote sensing image fusion in order to improve target recognition performance. Current fusion algorithms are mostly designed for specific purpose and have exponential complexity. We propose a ...
详细信息
Based on the research fruits of paper [1], the author introduces some new technologies into SBA collaborative supporting environment, including network technology (Internet / Web Service / Grid Computing), Artificial ...
详细信息
ISBN:
(纸本)9783642343865
Based on the research fruits of paper [1], the author introduces some new technologies into SBA collaborative supporting environment, including network technology (Internet / Web Service / Grid Computing), Artificial Intelligence and XMSF technology. Firstly, the author states a new integrated and intelligent infrastructure of SBA collaborative supporting environment which can fulfill the features and demands mentioned above;then some solved key technologies are explained in detail according to the latest research;at the end, good conclusions are verified by elementary application, which are, (1) the pre-setup prototype of SBA collaborative supporting environment are featured by networktized, intelligent, collaborative and integrated, as well as its good openness, security, extensibility and general, which can support the multidisciplinary team to collaboratively carry out the virtual R&D of complex products. (2) Combined with SBA integrated modeling, Hall of workshop of Metasynthetic Engineering, Life-cycle cost model and integration framework, the environment supports multi-location, multi-group, multi-disciplinary simulation applications, SOS (System of Systems) and qualitative-quantitative analysis, and is also supportive to the management, share and reuse of various simulation resources, which are very suitable for the SBA procedure of complex product.
In our society, the increasing number of information sources is still to be fully exploited for a global improvement in urban living. Among these, a big role is played by images and multimedia data (i.e. coming from C...
详细信息
Face recognition is an important research field of pattern *** to now,it caused researchers great concern from these fields,such as pattern recognition,computer vision,and physiology,and so *** recognition algorithms ...
详细信息
Learning is a capability that can be incorporated into software agents to handle the complexity of dynamic and unexpected situations, exploiting available artificial intelligence (AI) techniques. Despite design techni...
详细信息
We investigate the security of DTW, VQ and GMM methods that have been used in speaker authentication systems. We present attack models based on adversary knowledge. We start with naive adversaries without knowledge of...
详细信息
ISBN:
(纸本)9781601321916
We investigate the security of DTW, VQ and GMM methods that have been used in speaker authentication systems. We present attack models based on adversary knowledge. We start with naive adversaries without knowledge of an authentic speaker and develop them into highly knowledgeable adversaries who know the speaker's information, have the speaker's voice samples, acquire the speaker's template, and know an algorithm of the speaker authentication system. We propose an analysis-synthesis forgery in which the informed adversary can exploit information such as feature vectors from the template and a statistical probability from the voice samples of the target speakers to re-generate a forgery that can be used in remote or on-line authentication. We evaluate our scheme with two speech datasets. The results show that the proposed scheme outperforms other attack models reported in the literature.
In multi-patternintelligent CAI, select a most suitable instruction pattern is a key task. The paper adopts an algorithm for instruction pattern selection to calculate original adaptive-values, and a series of rule w...
详细信息
In multi-patternintelligent CAI, select a most suitable instruction pattern is a key task. The paper adopts an algorithm for instruction pattern selection to calculate original adaptive-values, and a series of rule was established to adjust these adaptive-values. Based on the theory of Deterministic Finite Automata, The adaptive algorithm for instruction pattern adjustment was proposed. It can adjust the selected instruction pattern dynamically. The experimental results show that the algorithm is a valid method on improving the adaptability in intelligent CAI.
The proceedings contain 40 papers. The topics discussed include: strategic points to minimize time cost for decision making under asynchronous time constraints;a recommender system for infrequent purchased products ba...
ISBN:
(纸本)9783642243950
The proceedings contain 40 papers. The topics discussed include: strategic points to minimize time cost for decision making under asynchronous time constraints;a recommender system for infrequent purchased products based on user navigation and product review data;forming buyer coalition schemes with ontologies in E-Marketplaces;toward a framework for assessing E-Marketplace service quality;relaxing queries based on XML structure and content preferences;automatic extraction rules generation based on XPath pattern learning;an XML-based representational document format for FRBR;a framework for XML schema integration via conceptual model;probability distribution-based QoS analysis for web service composition;and from ASTD access control policies to WS-BPEL processes deployed in a SOA environment.
暂无评论