检索结果-内蒙古大学图书馆

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Chen-Chia Chuang Chih-Ching Hsiao Jin-Tsong Jeng Department of Information and Eecmnic Commerce Kainan University Taoyuan Taiwan Department of Electrical Engineering Fortune Institute of Technology Kaohsiung Taiwan Department of Computer Science and Information Engineering National Huwei Institute of Technology Taiwan

ISBN: (纸本)0780378652

The TSK type of fuzzy models has attracted a great attention of the fuzzy modeling community due to their good performance in various applications. In the literature, some approaches for modeling TSK fuzzy rules have been proposed. Most of them define their fuzzy subspaces based on the idea of training data being close enough instead of having similar functions. Recently, a new approach, fuzzy c-regression model (FCRM) clustering algorithm, is proposed to construct TSK fuzzy models. However, this approach does not take into account the training data with outliers. In order to overcome the effects of outliers, a robust TSK fuzzy modeling with outliers has been proposed. It is worth noting that this approach may need more computation time due to complicated formulas. Hence, a novel TSK fuzzy modeling approach with outliers is presented in this paper. In this approach, robust fuzzy regression (RFR) clustering algorithm is proposed to simultaneously define fuzzy subspaces and find the parameters in the consequent parts of TSK rules. In the clustering process, the similarity measure is used to reduce the redundant rules. To obtain a more precision model that is not affected by outliers, an annealing robust BP learning algorithm is employed. From the simulation results, the proposed TSK fuzzy model approach indeed showed superior performance.

关键词： Clustering algorithms Robustness backpropagation algorithms Training data Machine learning algorithms Fuzzy systems Machine learning Business Annealing Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A fast learning algorithm of neural networks by changing error functions

A fast learning algorithm of neural networks by changing err...

引用

International Conference on Neural Networks and Signal Processing

作者： Minghu Jiang Beixing Deng Bin Wang Bo Zhang Dept. of Chinese Language Tsinghua Univ. Beijing P.R.China Dept. of Electronics Eng. Tsinghua Univ. Beijing P.R.China Dept of Computer Science & Tech. Tsinghua Univ. Beijing P.R.China

ISBN: (纸本)0780377028

In order to improve the training speed of multilayer feedforward neural networks, we propose and explore a new fast backpropagation (BP) algorithms obtained by changing the error functions, in case using the Fourier kernel function as alternative functions; to overcome the conventional BP learning problems of getting stuck into local minima or slow convergence. Our experimental results demonstrate the effectiveness of the modified error functions since the training speed is faster than that of existing fast methods.

关键词： Neural networks Computer errors Multi-layer neural network Algorithm design and analysis Computational linguistics Natural languages Computer science backpropagation algorithms Kernel Convergence

来源：评论

学校读者我要写书评

暂无评论

Neuro-textural classification of indian urban environment

Neuro-textural classification of indian urban environment

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： V. Pathak O. Dikshit Department of Civil Engineering IIT Kanpur Kanpur Uttar Pradesh India

来源：评论

学校读者我要写书评

暂无评论

A neuro-genetic algorithm approach for solving the inverse kinematics of robotic manipulators

A neuro-genetic algorithm approach for solving the inverse k...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： P. Karlra N.R. Prakash Dept. of Production Eng. Punjab Eng. Coll. Chandigarh India Department of Electronics Engineering Punjab Engineering College Chandigarh India

The inverse kinematics solution of a robotic manipulator requires the solution of non-linear equations having transcendental functions and involving time-consuming calculations. Artificial neural networks with their massively parallel architecture are natural candidates for providing a solution to this problem. In this work, a neuro-genetic algorithm approach is used to obtain the inverse kinematics solution of a robotic manipulator. A multi-layered feed-forward neural network architecture is used. The weights of the neural network are obtained during the training phase using a real-coded genetic algorithm. This training algorithm does not suffer from the usual drawbacks of the backpropagation learning algorithm. The approach is used to obtain the inverse kinematics solution of a planar robotic manipulator.

关键词： Kinematics Robots Manipulators Artificial neural networks backpropagation algorithms Nonlinear equations Parallel architectures Feedforward systems Neural networks Multi-layer neural network

来源：评论

学校读者我要写书评

暂无评论

Adaptive particle swarm optimisation for high-dimensional highly convex search spaces

Adaptive particle swarm optimisation for high-dimensional hi...

引用

Congress on Evolutionary Computation

作者： D. Tsou C. MacNish School of Computer Science & Software Engineering University of Western Australia Crawley WA Australia

The particle swarm optimisation (PSO) algorithm has been established as a useful global optimisation algorithm for multidimensional search spaces. A practical example is its success in training feed-forward neural networks. Such successes, however, must be judged relative to the complexity of the search space. We show that the effectiveness of the PSO algorithm breaks down when extended to high-dimensional "highly convex" search spaces, such as those found in training recurrent neural networks. A comparative study of backpropagation methods reveals the importance of an adaptive learning rate to their success. We briefly review the physics of the particle swarm optimiser, and use this view to introduce an analogous adaptive time step. Finally we demonstrate that the new adaptive algorithm shows improved performance on the recurrent network training problem.

关键词： Particle swarm optimization Recurrent neural networks backpropagation algorithms Neural networks Feedforward systems Feedforward neural networks Transfer functions Birds Computer science Software engineering

来源：评论

学校读者我要写书评

暂无评论

An adaptive power amplifier lineariser based on a multilayer perceptron

An adaptive power amplifier lineariser based on a multilayer...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： N. Naskas Y. Papananos Microelectronic Circuit Design Group National and Technical University of Athens Zografou Greece

In this paper, a RF power amplifier (PA) linearisation method base on a multilayer perceptron (MLP) neural network is proposed. The method is an alternative to the digital baseband predistortion. The predistortion component is a single MLP with a dual output and single input. For the training of the MLP the response of the PA, in a training ramp, and the backpropagation (BP) training algorithm are used. After the training process, the MLP is capable of compensating both the amplitude-to-amplitude (AM/AM) and amplitude-to-phase modulation (AM/PM) that PA introduces. A method's prototype has been constructed; this is according to the author's knowledge the first published experimental PA predistorter that employs MLP. Measurement results reveal a considerable improvement in the adjacent channel interference (ACI) that reaches 25 dB.

关键词： Power amplifiers Multilayer perceptrons Radiofrequency amplifiers Predistortion Radio frequency Neural networks Multi-layer neural network Baseband backpropagation algorithms Amplitude modulation

来源：评论

学校读者我要写书评

暂无评论

backpropagation learning for a fuzzy controller with partitioned membership functions

Backpropagation learning for a fuzzy controller with partiti...

引用

Annual Meeting of the North-American-Fuzzy-Information-Processing-Society

作者： Adams, JM Rattan, KS Wright State Univ Dayton OH 45435 USA

ISBN: (纸本)0780374614

A back propagation learning method is develped for partitioned, triangular, fuzzy input membership functions to account for the coupled nature of the function parameters. Partitioned, triangular input membership functions are common in industrial fuzzy applications. The resulting algorithm is applied to a Mamdani fuzzy logic system with product-sum inference and weighted-average defuzzification. The algorithm is developed from the standard backpropagation method with the complete impact of each input parameter change included in the partial derivative expansion of the system. The algorithm is applied to tune the input parameters of a controller for a two-link, planar robot. The system response is demonstrated for a set of commands which create cross-coupling through both centrifugal and Coriolis forces.

关键词： Aerospace industry backpropagation algorithms Fuzzy control Fuzzy logic Inference algorithms Learning systems Marine vehicles Partitioning algorithms Robots Standards development

来源：评论

学校读者我要写书评

暂无评论

Support vector black-box interpretation in ventricular arrhythmia discrimination

引用

IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE 2002年第1期21卷 27-35页

作者： Rojo-Alvarez, JL Arena-Maíz, A Artés-Rodríguez, A Univ Carlos III Madrid Escuela Politecn Superior Depto Teoria Senal & Comunicac Madrid 28911 Spain Hosp GU Gregorio Maranon Dept Cardiol Madrid Spain

A new discrimination algorithm, based on the analysis of ventricular electrogram (EGM) onset, was proposed in order to discriminate between supraventricular and ventricular tachycardias (SVTs and VTs) in implantable cardioverter defibrillators (ICDs). Due to the absence of a detailed statistical model for the ventricular activation, this algorithm was based on a support vector method (SVM) learning machine plus bootstrap resampling to avoid overfitting. This SVM classifier was trained with available arrhythmia episodes, so that it can be viewed as containing a statistical model for the differential diagnosis. However, the black-box model character of any learning machine presents problems in a clinical environment. A solution is the extraction of the statistical information enclosed in the black-box model. The SVM could be appropriate for this purpose, given that the support vectors represent the critical samples for the classification task. In this article we propose two SVM-oriented analyses and their use in building two new differential diagnosis algorithms based on the ventricular EGM onset criterion

关键词： Support vector machines Support vector machine classification Strontium Cardiology Covariance matrix Algorithm design and analysis Machine learning Mathematical model backpropagation algorithms Kernel

来源：评论

学校读者我要写书评

暂无评论

Predictive neural network modeling of pH and electrical conductivity in deep-trough hydroponics

引用

TRANSACTIONS OF THE ASAE 2002年第6期45卷 2007-2015页

作者： Ferentinos, KP Albright, LD Cornell Univ Dept Biol & Environm Engn Ithaca NY USA

A model is presented that predicts pH and electrical conductivity (EC) changes in the root zone of lettuce (Lactuca sativa cv. Vivaldi) grown in a deep-trough hydroponic system. A feedforward neural network is the basis of that modeling. The neural network model has nine inputs (pH, EC, nutrient solution temperature, air temperature, relative humidity, light intensity, plant age, amount of added acid, and amount of added base) and two outputs (pH and EC at the next time step). The most suitable and accurate combination of network architecture and training method was one hidden layer with nine hidden nodes, trained with the quasi-Newton backpropagation algorithm. The model proved capable of predicting pH at the next 20-minute time step within 0.01 pH units and EC within 5 muScm(-1). Simpler prediction methods, such as linear extrapolation and the "lazy man" prediction (in which "prediction" is the value of the previous time step), gave comparable accuracy much of the time. However, they performed poorly in situations where the control actions of the system had been activated and produced relatively rapid changes in the predicted parameters. In those cases, the neural network model did not encounter any difficulties predicting the rapid changes. Thus, the developed model successfully identified dynamic processes in the root zone of the hydroponic system and accurately predicted one-step-ahead values of pH and EC.

关键词： neural network modeling hydroponics pH electrical conductivity backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

Feedback error learning control using adaptive fuzzy network to control one linear actuator hopping robot

Feedback error learning control using adaptive fuzzy network...

引用

Asia-Pacific Conference on Circuits and Systems

作者： Kuswadi, S Takahashi, A Ohnishi, A Sampei, M Nakaura, S Tokyo Inst Technol Meguro Ku Tokyo 152 Japan

ISBN: (纸本)0780376900

This paper addresses the control method of one linear actuator hopping robot in a plane by using feedback error learning scheme. Adaptive fuzzy network was used in this scheme, and backpropagation techniques was utilized as learning algorithm. The robot consist of a body and a leg, which are in contact with a sufficiently wide horizontal ground;both axe fixed rigidly. We consider utilizing the starting time of actuation of actuator - when robot in stance phase - to control the gait. By simulation, the continuous hopping gait was realized.

关键词： Adaptive control Adaptive systems backpropagation algorithms Error correction Fuzzy control Hydraulic actuators Legged locomotion Linear feedback control systems Programmable control Robots

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：