检索结果-南通市图书馆

International Conference on Computational Techniques and Artificial Intelligence(ICCTAI’2011);International Conference on Advances in Electrical and Electronics Engineering(ICAEE’2011);International Conference on Mechanical,Automobile and Robotics Engineering(ICMAR’2011);International Conference on Management,Behavioral Sciences and Economics Issues(ICMBSE’2011);International Conference on Chemical,Environmental and Biological Sciences(ICCEBS’2011);International Conference on Biotechnology and Pharmaceutical Sciences(ICBPS’2011)

作者： Kazuaki Maeda the Department of Business Administration and Information Science Chubu University

This paper describes RugsOn, a new representation written in a text-based data format. The design principle of RugsOn is good readability and simplicity of structured data representation. One feature of RugsOn is a domain specific language to represent structured data. It is similar as JSON, but syntax of RugsOn is carefully chosen for multiple programming languages. Another feature is an executable representation. Once RugsOn-related definitions are loaded into a runtime environment, the representation can be executed corresponding to the definitions. Utility programs are available to read/write structured data to persistent storage-media, or to traverse the structured data. A program generator was developed to create Ruby, Groovy, Scala and Java programs from RugsOn definitions. In the author’s experience, productivity was improved in the design and implementation of programs that manipulate structured data.

关键词： data representation Structured data Domain Specific Languages

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Approximate Processing Element Design and Analysis for the Implementation of CNN Accelerators

引用

Journal of Computer Science & Technology 2023年第2期38卷 309-327页

作者：李彤姜红兰莫海韩杰刘雷波毛志刚 Department of Micro-Nano Electronics Shanghai Jiao Tong UniversityShanghai 200240China School of Integrated Circuits Tsinghua UniversityBeijing 100084China Department of Electrical and Computer Engineering University of AlbertaEdmontonAB T6G 1H9Canada

As a primary computation unit,a processing element(PE)is key to the energy efficiency of a convolutional neural network(CNN)*** advantage of the inherent error tolerance of CNNs,approximate computing with high hardware efficiency has been considered for implementing the computation units of CNN ***,individual approximate designs such as multipliers and adders can only achieve limited accuracy and hardware *** this paper,an approximate PE is dedicatedly devised for CNN accelerators by synergistically considering the data representation,multiplication and *** approximate data format is defined for the weights using stochastic *** data format enables a simple implementation of multiplication by using small lookup tables,an adder and a *** approximate accumulators are further proposed for the product accumulation in the *** with the exact 8-bit fixed-point design,the proposed PE saves more than 29%and 20%in power-delay product for 3×3 and 5×5 sum of products,***,compared with the PEs consisting of state-of-the-art approximate multipliers,the proposed design shows significantly smaller error bias with lower hardware ***,the application of the approximate PEs in CNN accelerators is analyzed by implementing a multi-task CNN for face detection and *** conclude that 1)an approximate PE is more effective for face detection than for alignment,2)an approximate PE with high statistically-measured accuracy does not necessarily result in good quality in face detection,and 3)properly increasing the number of PEs in a CNN accelerator can improve its power and energy efficiency.

关键词： approximate computing convolutional neural network(CNN) sum of products(SoP) data representation multiplier

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Comparisons of three data storage models in parametric temporal databases

引用

Journal of Central South University 2013年第7期20卷 1919-1927页

作者： Seo-Young NOH Shashi K. GADIA Haengjin JANG Supercomputing Center Korea Institute of Science and Technology Information Department of Computer Science Iowa State University

The parametric temporal data model captures a real world entity in a single tuple, which reduces query language complexity. Such a data model, however, is difficult to be implemented on top of conventional databases because of its unfixed attribute sizes. XML is a matured technology and can be an elegant solution for such challenge. Representing data in XML trigger a question about storage efficiency. The goal of this work is to provide a straightforward answer to such a question. To this end, we compare three different storage models for the parametric temporal data model and show that XML is not worse than any other approaches. Furthermore, XML outperforms the other storages under certain conditions. Therefore, our simulation results provide a positive indication that the myth about XML is not true in the parametric temporal data model.

关键词： data representation parametric data model XML-based representation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

VisuaLizations As Intermediate representations (VLAIR): An approach for applying deep learning-based computer vision to non-image-based data

引用

Visual Informatics 2022年第3期6卷 35-50页

作者： Ai Jiang Miguel A.Nacenta Juan Ye School of Computer Science University of St AndrewsUK University of Victoria Canada

Deep learning algorithms increasingly support automated systems in areas such as human activity recognition and purchase *** identify a current trend in which data is transformed first into abstract visualizations and then processed by a computer vision deep learning *** call this VisuaLization As Intermediate representation(VLAIR)and believe that it can be instrumental to support accurate recognition in a number of fields while also enhancing humans’ability to interpret deep learning models for debugging purposes or for personal *** this paper we describe the potential advantages of this approach and explore various visualization mappings and deep learning *** evaluate several VLAIR alternatives for a specific problem(human activity recognition in an apartment)and show that VLAIR attains classification accuracy above classical machine learning algorithms and several other non-image-based deep learning algorithms with several data representations.

关键词： Information visualization Convolutional neural networks Human activity recognition Smart homes data representation Intermediate representations Interpretability Machine learning Deep learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Role Assignment and Cooperation of Ontology and Object-Oriented Principle in Construction of Digital Product Model

引用

Tsinghua Science and Technology 2009年第S1期14卷 71-76页

作者：上官景昌阎艳刘海涛王国新赵博 School of Mechanical and Vehicle Engineering Beijing Institute of Technology R & D Center Shandong Wuzheng Group Ltd. Co.

Powerful expressive ability of semantic information, to be easily computed and flexibility are basic features of digital product model (DPM). Using ontology and object-oriented principle (OOP) together to cope with problems in modeling is brought forward in this paper. The two are widely used and do well in modeling, but they each alone cannot cope with all issues and new challenges. Three basic requests are pointed out in DPM modeling. Status, problems, and root of current non-semantic and semantic models are introduced. Ontology, OOP, and their difference are introduced. It is found that the two are entirely complementary with each other. How to assign the roles and to cooperate for the two in coping with the three basic issues in DPM modeling are explained in detail.

关键词： ontology object-oriented principle digital product model data representation role assignment and cooperation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Predicting the daily return direction of the stock market using hybrid machine learning algorithms

引用

Financial Innovation 2019年第1期5卷 435-454页

作者： Xiao Zhong David Enke Graduate School of Management Clark University313B Carlson Hall950 Main StreetWorcesterMA 01610USA Laboratory for Investment and Financial Engineering Department of Engineering Management and Systems

Big data analytic techniques associated with machine learning algorithms are playing an increasingly important role in various application fields,including stock market ***,few studies have focused on forecasting daily stock market returns,especially when using powerful machine learning techniques,such as deep neural networks(DNNs),to perform the *** employ various deep learning algorithms based on the combination of network structure,activation function,and model parameters,with their performance depending on the format of the data *** paper presents a comprehensive big data analytics process to predict the daily return direction of the SPDR S&P 500 ETF(ticker symbol:SPY)based on 60 financial and economic *** and traditional artificial neural networks(ANNs)are then deployed over the entire preprocessed but untransformed dataset,along with two datasets transformed via principal component analysis(PCA),to predict the daily direction of future stock market index *** controlling for overfitting,a pattern for the classification accuracy of the DNNs is detected and demonstrated as the number of the hidden layers increases gradually from 12 to ***,a set of hypothesis testing procedures are implemented on the classification,and the simulation results show that the DNNs using two PCA-represented datasets give significantly higher classification accuracy than those using the entire untransformed dataset,as well as several other hybrid machine learning *** addition,the trading strategies guided by the DNN classification process based on PCA-represented data perform slightly better than the others tested,including in a comparison against two standard benchmarks.

关键词： Daily stock return forecasting Return direction classification data representation Hybrid machine learning algorithms Deep neural networks(DNNs) Trading strategies

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Constrained Graph Concept Factorization for Image Clustering

Constrained Graph Concept Factorization for Image Clustering

引用

第26届中国控制与决策会议

作者： Yuqing Shi Shiqiang Du Weilan Wang School of Electrical Engineering Northwest University for Nationalities School of Mathematics and Computer Science Northwest University for Nationalities

ISBN: (纸本)9781479937097

Matrix factorization techniques have been frequently applied in data representation and pattern recognition. One of them is Concept Factorization（CF）, which is a new matrix decomposition technique for data representation. In this paper, we propose a novel semi-supervised matrix factorization algorithm, called Constrained Graph Concept Factorization（CGCF）, which incorporates the label information as additional constraints. Specifically, CGCF preserves the intrinsic geometry of data as regularized term and use the label information as semi-supervised learning, it makes nearby samples with the same class-label are more compact, and nearby classes are separated. An efficient multiplicative updating procedure was produced along with its theoretic justification of the algorithmic convergence. Compared with NMF, GNMF, CF, LCCF and Kmeans, experiment results on ORL and YALE face databases have shown that the proposed method achieves better clustering results.

关键词： data representation Concept Factorization(CF) Semi-supervised Learning Clustering

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Research and Implementation of Computer Simulation System for Neural Networks

Research and Implementation of Computer Simulation System fo...

引用

2002年第6届信号处理国际会议

作者： Baxter,D.A. Byrne,J.H. Mcdieal School University of Tcxas at Houston TexasU.S.A Mcdieal School University of Tcxas at Houston TexasU.S.A

＜正＞ The ability of a neural network to proces;information and to generate a specific pattern of electrical activity is dependent on both the intrinsic biophysical properties of the individual neurons in the network and their pattern of synaptic connectivity. Through the analysis of its biophysical and biochemical structure, and incorporation informatior science into medical science, computer simulations can be used to verify the known and explore the unknown, and will certainly be very significant to biomedical fields. In this paper one computer simulation system for neural networks was designed and implemented including system architecture, equivalent circuit, mathematical modeling, data representation, etc. The system architecture was designed as pyramid frame with open, controllable and measurable properties. It was implemented in platform-independent JAVA language with friendly graphical interface. And it has been widely applied.

关键词： Neural network Computer simulation Mathematical modeling data representation

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：