检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Yangqiu Song Changshui Zhang State Key Laboratory of Intelligent Technology and Systems Department of Automation Tsinghua University Beijing China

Feedforward neural networks are popular tools for nonlinear regression and classification problems. Gaussian Process (GP) can be viewed as an RBF neural network which have infinite number of hidden neurons. On regression problems, they can predict both the mean value and the variance of the given sample. Boosting is one of the most important recent developments in machine learning. Classification problems have dominated research on boosting to date. On the other hand, the application of boosting of regression has received less investigation. In this paper, we develop two boosting methods of GPs for regression according to the characteristic of them. We compare the performance of our ensembles with other boosting algorithms and find that our methods are more stable and essentially have less over-fitting problems than the other methods.

关键词： Boosting Gaussian processes Neural networks Feedforward neural networks Laboratories intelligent systems Automation Feeds Neurons Machine learning

来源：评论

学校读者我要写书评

暂无评论

Assessing features for electroencephalographic signal categorization

Assessing features for electroencephalographic signal catego...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shiliang Sun Changshui Zhang State Key Laboratory of Intelligent Technology and Systems Department of Automation Tsinghua University Beijing China

ISBN: (纸本)0780388747

The classification of electroencephalographic (EEG) signals is an important issue in the ongoing research of brain-computer interface (BCI) technology. One such BCI uses slow cortical potential measures to infer user intent from the original brain activity. Seven features based on the standard low-level signal properties are evaluated for their ability to classify brain activities, and thus make up for the scarcity of signal features for the current EEG signal categorization. In addition, a paradigm is proposed to select effective low-level features for EEG signal classification. Combining the features selected by the paradigm with the DC value of slow cortical potentials for categorization based on a Bayesian classifier, we obtained significant improvement on classification accuracy for data set Ia of the BCI competition 2003, which is a typical representative of one kind of BCI data.

关键词： Electroencephalography Brain Laboratories Pattern classification Communication system control Muscles Rhythm Speech processing Biomedical signal processing Sun

来源：评论

学校读者我要写书评

暂无评论

A fixed-point ICA algorithm with initialization constraint

A fixed-point ICA algorithm with initialization constraint

引用

International Conference on Communications, Circuits and systems (ICCCAS)

作者： Bin Wang Wenkai Lu State Key Laboratory of Intelligent Technology and Systems Department of Automation Tsinghua University Beijing China

ISBN: (纸本)0780390156

We propose a novel approach, the fixed-point algorithm (FastICA) with initialization constraint, for performing independent component analysis (ICA). In order to achieve a reliable convergence during estimating the blind source components, both the third- and fourth-order statistics are taken into account when diagonalizing the cumulant tensors. By combining these high-order statistics, an initialization constraint is introduced into the decomposition procedure of the independent components by FastICA. The experimental results demonstrate that the improved algorithm can achieve a better performance than the original FastICA without increasing the computation cost dramatically. The simulations involving source signals with different distributions show that our algorithm can adapt most source signals, including some complicated and asymmetric distributions.

关键词： Independent component analysis Signal processing algorithms Multidimensional signal processing Speech Statistical distributions Computational efficiency Statistical analysis Signal analysis Laboratories intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A modified coding scheme based on region quality using JPEG2000

A modified coding scheme based on region quality using JPEG2...

引用

International Symposium on Communications and Information Technologies (ISCIT)

作者： Guoqiang Zhou Shengjin Wang Xiaoqing Ding State Key Laboratory of Intelligent Technology and Systems Department of Electronic Engineering Tsinghua University China

The efficient use of channel bandwidth is one of the main issues in transmitting of image/video data. Rate control or rate allocation is necessary to control the bitrate of image coding such that it meets the channel bandwidth requirement. In this paper, we present a modified coding scheme based on region quality using JPEG2000. This scheme can achieve efficient utilization of the bandwidth as well as a high compression ration, which enables it play an important role in many fields such as transmission of satellite image, medical image and image communication in 3G.

关键词： Image coding Transform coding Size control Bandwidth Wavelet coefficients Bit rate Discrete wavelet transforms Rate-distortion Optimization methods Image quality

来源：评论

学校读者我要写书评

暂无评论

Markov跳变线性奇异摄动系统鲁棒H∞控制

引用

自动化学报 2005年第5期31卷 779-781页

作者：刘华平孙富春李春文孙增圻 Department of Computer Science and Technology Tsinghua University Beijing 100084State Key Laboratory of Intelligent Technology and Systems Beijing 100084 Department of Automation Tsinghua University Beijing 100084 Department of Computer Science and Technology Tsinghua University Beijing 100084

In this paper, we study the robust control for uncertain Markov jump linear singularly perturbed systems (MJLSPS), whose transition probability matrix is unknown. An improved heuristic algorithm is proposed to solve the nonlinear matrix inequalities. The results of this paper can apply not only to standard, but also to nonstandard MJLSPS. Moreover, the proposed approach is independent of the perturbation parameter and therefore avoids the ill-conditioned numerical problems.

关键词： Markov过程跳变线性奇异系统鲁棒控制矩阵不等式

来源：评论

学校读者我要写书评

暂无评论

A new transductive support vector machine approach to text categorization

A new transductive support vector machine approach to text c...

引用

IEEE International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE)

作者： Fan Sun Maosong Sun State Key Laboratory of Intelligent Technology and Systems Department of Computer Science & Technology Tsinghua University Beijing China

Transductive inference is well suited for text categorization tasks with an enormous amount of unlabeled data in addition to a small number of labeled data. We present a new transductive support vector machine approach for text categorization in order to make use of the large amount of unlabeled data efficiently. In our experiments the performance of transductive methods greatly exceeds that of conventional SVM. Experimental results also show that our algorithm outperforms Joachims' TSVM, especially when there is a significant deviation between the distribution of training and test data.

关键词： Support vector machines Text categorization Testing Machine learning Training data Simulated annealing Sun Support vector machine classification Inference algorithms Laboratories

来源：评论

学校读者我要写书评

暂无评论

A theory of computation based on quantum logic (I)

A theory of computation based on quantum logic (I)

引用

IEEE International Conference on Granular Computing (GRC)

作者： Mingsheng Ying State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China

Summary form only given. The (meta) logic underlying classical theory of computation is Boolean (two-valued) logic. Quantum logic was proposed by Birkhoff and von Neumann as a logic of quantum mechanics. It is currently understood as a logic whose truth values are taken from an orthomodular lattice. The major difference between Boolean logic and quantum logic is that the latter does not enjoy distributivity in general. The rapid development of quantum computation in recent years stimulates us to establish a theory of computation based on quantum logic. The present paper is the first step toward such a new theory and it focuses on the simplest models of computation, namely finite automata. We introduce the notion of orthomodular lattice-valued (quantum) automaton. The Kleene theorem about equivalence of regular expressions and finite automata is generalized into quantum logic. We also present a pumping lemma for orthomodular lattice-valued regular languages.

关键词： Quantum computing Quantum mechanics Logic Automata Boolean functions intelligent systems Computer science Artificial intelligence Laboratories Lattices

来源：评论

学校读者我要写书评

暂无评论

HMM based terrain elevation matching algorithm

引用

Zidonghua Xuebao/Acta Automatica Sinica 2005年第6期31卷 960-964页

作者： Feng, Qing-Tang Shen, Lin-Cheng Chang, Wen-Sen Ye, Yuan-Yuan State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing 100084 China School of Electromechanical Engineering and Automation National University of Defense Technology Hunan 410073 China

Terrain-aided navigation (TAN) uses terrain height variations under an aircraft to render the position estimate to bound the inertial navigation system (INS) error. This paper proposes a new terrain elevation matching (TEM) model, viz. Hidden-Markov-model (HMM) based TEM (HMMTEM) model. With the given model, an HMMTEM algorithm using Viterbi algorithm is designed and implemented to estimate the position error in INS. The simulation results show that HMMTEM algorithm can better improve the positioning precision of autonomous navigation than SITAN algorithm.

关键词： Air navigation

来源：评论

学校读者我要写书评

暂无评论

Quotient space model of hierarchical query-by-humming system

Quotient space model of hierarchical query-by-humming system

引用

IEEE International Conference on Granular Computing (GRC)

作者： Zhi Wang Bo Zhang State Key Laboratory of Intelligent Technology and Systems Computer Science Department Tsinghua University Beijing China

In this paper, we put ideas of granular computing into the application of query-by-humming. Leading by quotient space theory of problem solving, we present a quotient space model of hierarchical query-by-humming system, which do search in two stages. The first is searching in the quotient space to obtain high recall rate and a narrowed possible region with accepted speed. The second step is doing accurate but relatively slow search in the small original space to achieve high precision. In addition, we improve the previous dynamic programming techniques for melody matching, which tolerate the input error more reasonably. We also compare our hierarchical method with the previous flat note-based algorithm and frame-based algorithm on MIDI-encoded database of Chinese music and obtain promising results both in efficiency and accuracy.

关键词： Space technology Spatial databases intelligent systems Computer science Problem-solving Costs Computer applications Application software Dynamic programming Robustness

来源：评论

学校读者我要写书评

暂无评论

Hybrid dynamic scheduling framework using layered fuzzy inference and RBF neural network

Hybrid dynamic scheduling framework using layered fuzzy infe...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Yu-Jun Chen Jia-Xin Wang Ze-Hong Yang Yan-Nan Zhao State Key Laboratory of Intelligent Technology and Systems Department of Computer Science Tsinghua University Beijing China

Effective dynamic scheduling is an essential element in the process of intelligent road construction. The primary goal of this paper is to outline a two stage framework of dynamic scheduling for construction using layered fuzzy inference and radial basis function (RBF) neural network. The layered fuzzy inference presents an initial model which embeds the experts' knowledge by Zadah fuzzy theory and decision fusion. The RBF neural network adaptively adjusts the parameters of the initial model during the operation process. The experiment of the actual engineering problem shows that the scheduling results accord with the human knowledge and the training of the model needs less time compared with BP neural network. The proposed hybrid framework has been integrated in the practical asphalt road construction scheduling system.

关键词： Dynamic scheduling Fuzzy neural networks Neural networks Fuzzy systems Roads Artificial neural networks Humans Job shop scheduling intelligent networks Asphalt

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：