检索结果-内蒙古大学图书馆

American Control Conference 2005 (ACC)

作者： Huang, GH Xiong, ZH Shao, HH Shanghai Jiao Tong Univ Inst Automat Shanghai 200030 Peoples R China

ISBN: (纸本)0780390989

A general and efficient design approach using covering neural classifier to cope with the high-dimensional and small sample size problem is proposed. For alleviating the computational burden, face features are first extracted by the principal component analysis (PCA). In order to avoid the influence of outlier classes and reduce the large overlapping of neighboring classes, a new weighted Fisher linear discriminant (WFLD) criterion is presented by weighting contributions of individual class pairs according to the Euclidian distance of the respective class means. A new learning algorithm is used to train the neural networks classifier, which uses the "sphere neighborhoods" to cover the input samples and draw up their distributions in the original space. Thus, the training problem of neural networks may be transformed into the covering problem of a point set, which avoids the iterative process, and overcomes the problem of longtime training of classical neural networks. Simulation results conducted on the ORL database show that the system achieves excellent performance both in terms of error rates of classification and learning efficiency.

关键词： Face recognition Neural networks Feature extraction Principal component analysis Shape measurement Data mining backpropagation algorithms Automation Position measurement Lighting

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control Using Neural Networks

引用

IEEE Control Systems 1995年第5期15卷 61-66页

作者： Draeger, Andreas Engell, Sebastian Ranke, Horst Process Control Group Department of Chemical Engineering University of Dortmund D-44221 Dortmund Germany

In this article, we present the application of a neural-network-based model predictive control scheme to control pH in a laboratory-scale neutralization reactor. We use a feedforward neural network as the nonlinear prediction model in an extended DMC-algorithm to control the pH-value. The training data set for the neural network was obtained from measurements of the inputs and outputs of the real plant operating with a PI-controller. Thus, no a priori information about the dynamics of the plant and no special operating conditions of the plant were needed to design the controller. The training algorithm used is a combination of an adaptive backpropagation algorithm that tunes the connection weights with a genetic algorithm to modify the slopes of the activation function of each neuron. This combination turned out to be very robust against getting caught in local minima and it is very insensitive to the initial settings of the weights of the network. Experimental results show that the resulting control algorithm performs much better than the conventional PI-controller which was used for the generation of the training data set.< >

关键词： Predictive models Predictive control Neural networks Training data backpropagation algorithms Laboratories Inductors Feedforward neural networks Genetic algorithms Neurons

来源：评论

学校读者我要写书评

暂无评论

Study of Neural Networks to Improve Performance for Character Recognition

Study of Neural Networks to Improve Performance for Characte...

引用

IEEE International Conference on Automation, Quality and Testing, Robotics

作者： Gheorghita, S. Munteanu, R. Enache, M. Tech Univ Cluj Napoca Fac Elect Engn Daicoviciu St 15 Cluj Napoca 40020 Romania Tech Univ Cluj Napoca Dept Automat Daicoviciu St 15 Cluj Napoca 40020 Romania

ISBN: (纸本)9781467307024

Three methods are proposed to improve the performance of a system based on feedforward neural networks, that is used for character recognition which are perturbed with noise up to 50%. Have been studied neural networks using backpropagation algorithm. The first element introduced in this study is to train the network in stages, using input data with noise, from 0 to 25% (steps 10,15,20,25) and then from 30% to 40% (steps 30,35,40). This approach has allowed fewer errors up to 1,2% for noise plateau 40%-50%. The second proposed method consists in introducing a vector of stability for the primary information, in stages of network training and then character recognition, with role to reduce the influence of noise on the input data. Stability vector proposed is a linear array with 5 constant parameters. The network used has 35 inputs, 16,20,25,30 or 50 nodes in the hidden layer and 26 outputs (one for each letter). The simulation and experimental results demonstrate that the proposed "vector of stability" can improve performance by decreasing the number of errors up to 1,7% for a neural network with 30 or 50 nodes in hidden layer. The third element proposed is to use reverse information (reverse the bits 0 with 1 and 1 with 0). Have been used two networks that process information. Then their outputs are analyzed and processed by a logic block. With this technique performances have been improved by decreasing the number of errors with 1%, 1.5% and 2.3% for 40%, 45% and 50% noise data.

关键词： Character recognition Neural network feedforward neural nets backpropagation algorithms linear arrays Chpher(0)

来源：评论

学校读者我要写书评

暂无评论

A hierarchical neuro-fuzzy system based on S-implications

A hierarchical neuro-fuzzy system based on S-implications

引用

International Joint Conference on Neural Networks

作者： Nowicki, R Scherer, R Rutkowski, L Czestochowa Tech Univ Dept Comp Engn PL-42200 Czestochowa Poland

In this paper we present a neuro-fuzzy structure of the Hierarchical Prioritized Structure (HPS) proposed by Yager. The HPS allows for easy hierarchization of a fuzzy rule-base. Our neuro-fuzzy system can be learned b... 详细信息

ISBN: (纸本)0780378989

关键词： fuzzy neural nets hierarchical systems backpropagation hierarchical neuro-fuzzy system S-implications hierarchical prioritized structure fuzzy rule-base backpropagation algorithm computationally efficient algorithm backpropagation algorithms Fuzzy neural networks Hierarchical systems back propagation fuzzy rule base Fuzzy systems efficient algorithm Hierarchical

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Formation Control for the Multi-Agent Coordination 16

Deep Learning Based Formation Control for the Multi-Agent Co...

引用

16th IEEE International Conference on Networking, Sensing and Control (ICNSC)

作者： Liu, Qishuai Moulay, Emmanuel Coirault, Patrick Hui, Qing Univ Nebraska Dept Elect & Comp Engn Lincoln NE 68588 USA Univ Poitiers CNRS UMR 7252 XLIM Poitiers France Univ Poitiers LIAS EA 6315 Poitiers France

ISBN: (纸本)9781728100845

Formation control of multi-agent systems has been an important task in the fields of automatic control and robotics. The aim of this paper is to develop a deep learning based formation control strategy for the multi-agent systems by using the backpropagation algorithm. Specifically, the deep learning network can be treated as the feedback controller, thus the multi-agent system can use the network output as its input to achieve the formation control. The algorithm has been tested on a multirobot system to verify the effectiveness of the proposed method.

关键词： backpropagation algorithms Feedback control Mathematical model Robot sensing systems Deep learning Control systems backpropagation

来源：评论

学校读者我要写书评

暂无评论

Stochastic Weight Update for Recurrent Networks 7

Stochastic Weight Update for Recurrent Networks

引用

Joint 7th International Conference on Soft Computing and Intelligent Systems (SCIS) and 15th International Symposium on Advanced Intelligent Systems (ISIS)

作者： Koscak, Juraj Jaksa, Rudolf Sincak, Peter Tech Univ Kosice Letna 9 Kosice 04200 Slovakia

ISBN: (纸本)9781479959556

Stochastic weight update is a variant of error back-propagation algorithm for learning of artificial neural networks. It allows for efficient topology-independent implementation of backpropagation through time for recurrent networks. In stochastic weight update scenario, constant number of weights and neurons is randomly selected and updated. This is in contrast to the classical ordered update, where all weights/neurons are always updated. In this paper we will study performance of stochastic weight update on recurrent neural networks using concept of feedforward network with added recurrent neurons.

关键词： backpropagation feedforward neural nets recurrent neural nets stochastic processes artificial neural network classical ordered update error back-propagation algorithm feedforward network recurrent network recurrent neural network recurrent neuron stochastic weight update scenario topology-independent implementation backpropagation backpropagation algorithms Convergence Educational institutions Network topology Neurons Topology

来源：评论

学校读者我要写书评

暂无评论

CMAS: an associative neural network alternative to backpropagation

引用

Proceedings of the IEEE 1990年第10期78卷 1561-1567页

作者： W.T. Miller F.H. Glanz L.G. Kraft Department of Electrical and Computer Engineering University of New Hampshire Durham NC USA

The CMAC (cerebellar model arithmetic computer) neural network, an alternative to backpropagated multilayer networks, is described. The following advantages of CMAC are discussed: local generalization, rapid algorithmic computation based on LMS (least-mean-square) training, incremental training, functional representation, output superposition, and a fast practical hardware realization. A geometrical explanation of how CMAC works is provided, and applications in robot control, pattern recognition, and signal processing are briefly described. Possible disadvantages of CMAC are that it does not have global generalization and that it can have noise due to hash coding. Care must be exercised (as with all neural networks) to assure that a low error solution will be learned.< >

关键词： Neural networks Quantum computing Multi-layer neural network Signal processing algorithms Digital arithmetic Computer networks backpropagation algorithms Least squares approximation Hardware Application software

来源：评论

学校读者我要写书评

暂无评论

Neural network training algorithms on parallel architectures for finance applications

Neural network training algorithms on parallel architectures...

引用

International Conference on Parallel Processing

作者： Thulasiram, RK Rahman, RM Thulasiraman, P Univ Manitoba Dept Comp Sci Winnipeg MB R3T 2N2 Canada

ISBN: (纸本)0769520189

We focus on the neural network training problem that could be used for price forecasting or other purposes in finance. We design and develop four different parallel and multithreaded backpropagation neural network algorithms: neuron and training set parallelism on a distributed memory architecture using MPI;loop-level (fine-grain) and coarse-grained parallelism in shared memory architecture using OpenMP We have conducted various experiments to study the performance of these algorithms and compared our results with a traditional autoregression model to establish accuracy of our results. The comparison between our MPI and OpenMP results suggest that the training set parallelism performs better than all the other types of parallelism considered in the study.

关键词： Algorithm design and analysis Application software backpropagation algorithms Economic forecasting Finance Memory architecture Neural networks Neurons Parallel architectures Parallel processing

来源：评论

学校读者我要写书评

暂无评论

A Multivariable Neural Controller for Automatic Ship Berthing

引用

IEEE Control Systems 1997年第4期17卷 31-45页

作者： Zhang, Yao Hearn, Grant E. Sen, Pratyush Department of Marine Technology University of Newcastle upon Tyne Newcastle uponb Tyne NE17RU United Kingdom

This article describes the development and application of a multivariable neural controller for automatic ship berthing. Following a brief review of various methods employed in automatic ship control, an online trained, backpropagation-based neural network controller is presented. The principal intention is to take advantage of the learning ability of neural networks, and to derive an autonomous neural control algorithm which is independent of the mathematical model of the ship. The proposed neural network controller is designed to adjust its parameters online from a direct evaluation of performance accuracy, thereby eliminating the need for off-line training and a "trainer" associated with supervised control. In addition, the nonlinearity of the rudder and the transfer lag of the propeller have been considered in the system design to increase the realism of the simulation. A series of simulation studies, which include wind disturbances and shallow water effects, have been undertaken to demonstrate the adaptive features and the robust performance of the proposed neural control scheme.

关键词： Automatic control Marine vehicles Neural networks backpropagation algorithms Mathematical model Propellers Programmable control Adaptive control Robust control

来源：评论

学校读者我要写书评

暂无评论

Growth-Phase Classification Using backpropagation and Probabilistic Neural Networks

引用

IFAC Proceedings Volumes 1999年第2期32卷 7568-7572页

作者： Laurent Simon M. Nazmul Karim Department of Chemical and Bioresource Engineering Colorado State University Fort Collins CO 80523 USA

backpropagation and probabilistic neural networks were implemented to classify 3 distinct phases of the batch growth-cycle: the lag, exponential and stationary phases. The microorganism used in the study was a recombinant strain of Bacillus subtilis DB428, genetically engineered to increase the production of β-lactamase. To identify the phases, a modified version of the Gompertz model was used. The analysis took into account the fact that the third derivative with respect to time of the growth curve intercepts the time-axis in two places. The fermentation time and the third derivative of the growth curve were used as inputs to the networks. The backpropagation neural network correctly classified 88% of the testing data. The classification index increased to 97% when the data were fed to the probabilistic neural network.

关键词： Neural network models Probabilistic models backpropagation algorithms Classification

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：