检索结果-内蒙古大学图书馆

5th international conference on intelligent data engineering and automated learning, ideal 2004

作者： Lee, Hyoung-Joo Cho, Sungzoon Department of Industrial Engineering Seoul National University San 56-1 Shillim-dong Kwanak-gu Seoul151-744 Korea Republic of

ISBN: (纸本)3540228810

A Gaussian mixture model (GMM) estimates a probability density function using the expectation-maximization algorithm. However, it may lead to a poor performance or inconsistency. this paper analytically shows that performance of a GMM can be improved in terms of Kullback-Leibler divergence with a committee of GMMs with different initial parameters. Simulations on synthetic datasets demonstrate that a committee of as few as 10 models outperforms a single model. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

AN NEW BELIEF RULE BASE REPRESENTATION SCHEME AND ITS GENERATION BY learning FROM EXAMPLES

引用

10th international conference on Fuzzy Logic and intelligent Technologies in Nuclear Science (FLINS)

作者： Liu, J. Martinez, L. Wang, H. Calzada, A. Chen, S. W. Univ Ulster Sch Comp & Math Coleraine BT52 1SA Londonderry North Ireland Univ Jaen Sch Comp Dept Comp Sci Jaen Spain

ISBN: (纸本)9789814417730

A new rule-based representation scheme is proposed with belief degrees embedded in the entire consequent terms and in the entire antecedent terms of each rule, which is shown to be capable of capturing uncertainty and nonlinear causal relationships in an integrated way. the overall representation and inference framework offers a further improvement and extension of the recently developed belief rule base inference methodology (called RIMER). Subsequently, a simple but efficient method for automatically generating such extended belief rule-base from numerical data is proposed involving neither time-consuming iterative learning procedure nor complicated rule generation mechanisms, which is mainly attributed to the new features of the ex-tended rule base with belief structures. then a case study in oil pipeline leak detection is provided to illustrate the proposed approaches.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Abnormal event detection via multi-instance dictionary learning

Abnormal event detection via multi-instance dictionary learn...

引用

13th international conference on intelligent data engineering and automated learning, ideal 2012

作者： Huo, Jing Gao, Yang Yang, Wanqi Yin, Hujun State Key Laboratory for Novel Software Technology Nanjing University China School of Electrical and Electronic Engineering University of Manchester United Kingdom

ISBN: (纸本)9783642326387

In this paper, we present a method for detecting abnormal events in videos. In the proposed method, we define an event containing several sub-events. Sub-events can be viewed as instances and an event as a bag of instances in the multi-instance learning formulation. Given labeled events but with the labels of sub-events unknown, the proposed method is able to learn a dictionary together with a classification function. the dictionary is capable of generating discriminant sparse codes of sub-events while the classification function is able to classify an event. this method is suited for scenarios where the label of a sub-event is ambiguous, while the label of a set of sub-events is definite and is easy to obtain. Once the sparse codes of sub-events are generated, the classification of an event is carried out according to the result given by the classification function. An efficient optimization procedure of the proposed method is presented. Experiments show that the method is able to detect abnormal events with comparable or improved accuracy compared with other methods. © 2012 Springer-Verlag.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

automated lecture template generation in CORDRA-based learning object repository

Automated lecture template generation in CORDRA-based learni...

引用

10th international conference on Advances in Web-Based learning, ICWL 2011

作者： Yen, Neil Y. Shih, Timothy K. Jin, Qun Lin, Li-Chieh Dept. of Human Informatics and Cognitive Sciences Waseda University Japan Dept. of Computer Science and Information Engineering National Central University Taiwan Digital Education Institute Institute for Information Industry Taiwan

ISBN: (纸本)9783642258121

Sharing resources and information on Internet has become an important activity for education. the MINE Registry, a branch of distributed repository, inherited the architecture of CORDRA has been developed for storing and sharing learning Objects. Following the usage experiences, especially those being utilized to generate the lecture, the interaction structure is defined to clarify the relationships among learning Objects. the methods to social network analysis are applied to quantify the implicit correlations and to evaluate the interdependency. In addition, an intelligent mining algorithm is proposed to explore the developed interaction structure and automatically generates lecture templates corresponding to the query criteria. the concentration of this study is to facilitate the complex and time-consuming process of creating lectures through a simple search mechanism. the implemented system has demonstrated the preliminary results and the feasibility are also revealed by the evaluation results. © 2011 Springer-Verlag.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

FETCH: A Memory-Efficient Replay Approach for Continual learning in Image Classification 24th

FETCH: A Memory-Efficient Replay Approach for Continual Lea...

引用

24th international conference on intelligent data engineering and automated learning, ideal 2023

作者： Weißflog, Markus Protzel, Peter Neubert, Peer Faculty of Electrical Engineering and Automation Technology Chemnitz University of Technology Chemnitz Germany Institute for Computational Visualistics University of Koblenz Koblenz Germany

ISBN: (纸本)9783031482311

Class-incremental continual learning is an important area of research, as static deep learning methods fail to adapt to changing tasks and data distributions. In previous works, promising results were achieved using replay and compressed replay techniques. In the field of regular replay, GDumb [23] achieved outstanding results but requires a large amount of memory. this problem can be addressed by compressed replay techniques. the goal of this work is to evaluate compressed replay in the pipeline of GDumb. We propose FETCH, a two-stage compression approach. First, the samples from the continual datastream are encoded by the early layers of a pre-trained neural network. Second, the samples are compressed before being stored in the episodic memory. Following GDumb, the remaining classification head is trained from scratch using only the decompressed samples from the reply memory. We evaluate FETCH in different scenarios and show that this approach can increase accuracy on CIFAR10 and CIFAR100. In our experiments, simple compression methods (e.g., quantization of tensors) outperform deep autoencoders. In the future, FETCH could serve as a baseline for benchmarking compressed replay learning in constrained memory scenarios. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

GPU-Based Acceleration of the Rao Optimization Algorithms: Application to the Solution of Large Systems of Nonlinear Equations 24th

GPU-Based Acceleration of the Rao Optimization Algorithms:...

引用

24th international conference on intelligent data engineering and automated learning, ideal 2023

作者： Silva, Bruno Lopes, Luiz Guerreiro Doctoral Program in Informatics Engineering University of Madeira Madeira Is. Funchal Portugal Regional Secretariat for Education Science and Technology Regional Government of Madeira Funchal Portugal Faculty of Exact Sciences and Engineering University of Madeira Madeira Is. Funchal9020-105 Portugal

ISBN: (纸本)9783031482311

In this paper, parallel GPU-based versions of the three Rao metaphor-less optimization algorithms are proposed and used to solve large-scale nonlinear equation systems, which are hard to solve with traditional numerical methods, particularly as the size of the systems get bigger. the parallel implementations of the Rao algorithms were performed in Julia and tested on a high-performance GeForce RTX 3090 GPU with 10 496 CUDA cores and 24 GB of GDDR6X VRAM using a set of challenging scalable systems of nonlinear equations. the computational experiments carried out demonstrated the efficiency of the proposed GPU-accelerated versions of the Rao optimization algorithms, with average speedups ranging from 57.10 × to 315.12 × for the set of test problems considered in this study. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

An Investigation on the Detection of Intrusions into a Network Using Convolutional Neural Networks 1

引用

10th international conference on Innovations in Computer Science and engineering, ICICSE 2022

作者： Patel, N.D. Singh, Ajeet TS Hyderabad500057 India SML2029 Research and Consulting Pvt Ltd Banjara Hills TS Hyderabad500034 India

ISBN: (数字)9789811974557

ISBN: (纸本)9789811974540

As attacks on the network environment are rapidly becoming more sophisticated and intelligent in the recent years, the limitations of the existing signature- based intrusion detection system are becoming more evident. In order to solve this problem, machine learning research on constructing automated network intrusion detection system (NIDS) is being actively conducted. NIDS model research using the convolution neural network (CNN) algorithm is conducted in this study. For image classification-based CNN algorithm learning, discretization of a continuous algorithm is added to the preprocessing step. the linear relationship between the predictor variables is converted into easy-to-read data, and then a square matrix is added. the pixel image structure matched to the matrix structure is learned on the model. Network packet data (UNSW-NB15) is used to consider the execution of the model, and accuracy, precision, and recall were used as statistical performance indicators. It is observed that the test results outperform for detecting specific attack categories. the proposed framework is giving 97.05% accuracy corresponding to DoS Exploits, fuzzers, generic, and reconnaissance attack classes. © 2023, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Giving voice to the internet by means of conversational agents

引用

15th international conference on intelligent data engineering and automated learning, ideal 2014

作者： Griol, David De Miguel, Araceli Sanchis Molina, José Manuel Universidad Carlos III de Madrid Avda. de la Universidad 30 28911 Leganés Spain

ISBN: (纸本)9783319108391

In this paper we present a proposal to develop conversational agents that avoids the effort of manually defining the dialog strategy for the agent and also takes into account the benefits of using current standards. In our proposal the dialog manager is trained by means of a POMDP-based methodology using a labeled dialog corpus automatically acquired using a user modeling technique. the statistical dialog model automatically selects the next system response. thus, system developers only need to define a set of files, each including a system prompt and the associated grammar to recognize user responses. We have applied this technique to develop a conversational agent in VoiceXML that provides information for planning a trip. © 2014 Springer international Publishing Switzerland.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

Design of Linguistically Interpretable Fuzzy Rule-Based Classifiers: A Short Review and Open Questions

引用

JOURNAL OF MULTIPLE-VALUED LOGIC AND SOFT COMPUTING 2011年第2-3期17卷 101-134页

作者： Ishibuchi, Hisao Kaisho, Yutaka Nojima, Yusuke Osaka Prefecture Univ Dept Comp Sci & Intelligent Syst Naka Ku Osaka 5998531 Japan

Fuzzy rule-based classifier design often involves conflicting criteria: accuracy and interpretability. this paper discusses the design of linguistically interpretable fuzzy rule-based classifiers. the emphasis of our discussions is placed on the linguistic interpretability of fuzzy rule-based classifiers rather than their accuracy. First we give a short survey on the design of fuzzy rule-based classifiers with linguistic conditions. Next we discuss the relation between the complexity of fuzzy partitions and their interpretability using fuzzy grids with different granularities. then we discuss the interpretability of fuzzy rule-based classifiers using simple numerical examples. We also discuss the interpretability of classification results by fuzzy rule-based classifiers. that is, we discuss the explanation ability of fuzzy rule-based classifiers to explain the classification result of each pattern in a human understandable manner. the main contribution of this paper is to demonstrate that we still have a number of open questions with respect to the interpretability of fuzzy rule-based classifiers.

关键词： Linguistic rules fuzzy systems fuzzy rule-based classifiers fuzzy classification interpretability

来源：评论

学校读者我要写书评

暂无评论

the categorisation of similar non-rigid biological objects by clustering local appearance patches

引用

5th international conference on intelligent data engineering and automated learning, ideal 2004

作者： Wang, Hongbin Culverhouse, Phil F. Centre for Interactive Intelligent Systems School of Computing Communications and Electronics University of Plymouth PlymouthPL4 8AA United Kingdom

ISBN: (纸本)3540228810

A novel approach is presented to the categorisation of non-rigid biological objects from unsegmented scenes in an unsupervised manner. the biological objects investigated are five phytoplankton species from the coastal waters of the European Union. the high morphological variability within each species and the high similarity between species make the categorisation task a challenge for both marine ecologists and machine vision systems. the framework developed takes a local appearance approach to learn the object model, which is done using a novel-clustering algorithm with minimal supervised information. Test objects are classified based on matches with local patches of high occurrence. Experiments show that the method achieves good results, given the difficulty of the task. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Clustering algorithms

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：