检索结果-内蒙古大学图书馆

The dependence identification neural network construction algorithm

IEEE TRANSACTIONS ON NEURAL NETWORKS 1996年第1期7卷 3-15页

作者： Moody, JO Antsaklis, PJ Department of Electrical Engineering University of Notre Dame Notre Dame IN USA

An algorithm for constructing and training multilayer neural networks, dependence identification, is presented in this paper. Its distinctive features are that i) it transforms the training problem into a set of quadratic optimization problems that are solved by a number of linear equations, ii) it constructs an appropriate network to meet the training specifications, and iii) the resulting network architecture and weights can be further refined with standard training algorithms, like backpropagation, giving a significant speedup in the development time of the neural network and decreasing the amount of trial and error usually associated with network development.

关键词： Neural networks Neurons backpropagation algorithms Iterative algorithms Transforms Equations Standards development Multi-layer neural network Intelligent networks

来源：评论

学校读者我要写书评

暂无评论

TRAINING THE HIGHER-ORDER MOMENT NEURAL ARRAY

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 1994年第7期42卷 1884-1887页

作者： PORTER, WA LIGADE, S Department of Electrical and Computer Engineering University of Alabama Huntsville Huntsville AL USA

The research summarized herein is concerned with an algorithm which stores information and provides a learning capability. This algorithm is affiliated with a class of neural networks which are referred to as higher order moment neural arrays. The algorithm may be viewed as a generalized training procedure for the affiliated networks.

关键词： Signal processing algorithms Multidimensional signal processing Digital filters Biomedical signal processing Array signal processing backpropagation algorithms Circuits Artificial neural networks Biological system modeling Neural networks

来源：评论

学校读者我要写书评

暂无评论

Fuzzy parameter adaptation in optimization: Some neural net training examples

引用

IEEE COMPUTATIONAL SCIENCE & ENGINEERING 1996年第1期3卷 57-65页

作者： Arabshahi, P Choi, JJ Marks, RJ Caudell, TP UNIV WASHINGTON SEATTLEWA 98195 BOEING CO COMP SERVSEATTLEWA 98124 UNIV NEW MEXICO ALBUQUERQUENM 87131

Many types of artificial neural networks require training to "learn" the tasks they will be called upon to do, which basically translates into properly setting the weights of the interneuron connections or "synapses" so that the network will give the desired output. Values of certain parameters in the algorithms used to train the networks must be chosen and then adapted or optimized carefully. Error backpropagation training of the multilayer perceptron, for example, requires judicious choice of the step and momentum parameters. The ART network requires choice of a vigilance parameter, while a learning rate must be selected for Kohonen networks. These parameters are typically chosen and adapted by a human "neural smith" using heuristic rules. For example, a smooth error surface in the backpropagation training of a layered perceptron suggests use of a long step, whereas a steep surface indicates a need for smaller steps. The heuristic description of the parameter selection is fuzzy. The terms "smooth," "long," "steep," and "smaller" are each fuzzy linguistic variables that can be quantified into a fuzzy inference engine. A properly designed fuzzy controller, then, can relieve the neural smith of some labor, and get the job done quicker and better. The concept has broader possible applications, beyond neural network training, to parameter selection and optimization generally.

关键词： Fuzzy neural networks Neural networks Fuzzy control Fuzzy sets Fuzzy systems Artificial neural networks backpropagation algorithms Subspace constraints Humans Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

An ArcGIS Tool for Modeling the Climate Envelope with Feed-Forward ANN

引用

APPLIED ARTIFICIAL INTELLIGENCE 2015年第3期29卷 233-242页

作者： Bede-Fazekas, Akos Horvath, Levente Trajer, Attila J. Gregorics, Tibor Corvinus Univ Budapest Dept Garden & Open Space Design H-1118 Budapest Hungary Corvinus Univ Budapest Dept Math & Informat H-1118 Budapest Hungary Univ Pannonia Dept Limnol Veszprem Hungary MTA PE Limnoecol Res Grp Veszprem Hungary Eotvos Lorand Univ Dept Software Technol & Methodol Budapest Hungary

This article is about the development and application of an ESRI ArcGIS tool that implements a multilayer, feed-forward artificial neural network (ANN) to study the climate envelopes of species. The supervised learning is achieved by a backpropagation algorithm. Based on the distribution and the grids of the climate (and edaphic data) of the reference and future periods, the tool predicts the future potential distribution of the studied species. The trained network can be saved and loaded. A modeling result based on the distribution of European larch (Larix decidua Mill.) is presented as a case study.

关键词： Modeling Climate Artificial neural networks backpropagation algorithms Larix decidua FEEDFORWARD

来源：评论

学校读者我要写书评

暂无评论

The cascade-correlation learning: A projection pursuit learning perspective

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1996年第2期7卷 278-289页

作者： Hwang, JN You, SS Lay, SR Jou, IC MINIST TRANSPORTAT & COMMUN TELECOMMUN LABS CHUNGLI 320 TAIWAN

Cascade-correlation (Cascor) is a popular supervised learning architecture that dynamically grows layers of hidden neurons of fixed nonlinear activations (e.g., sigmoids), so that the network topology (size, depth) can be efficiently determined. Similar to a cascade-correlation learning network (CCLN), a projection pursuit learning network (PPLN) also dynamically grows the hidden neurons. Unlike a CCLN where cascaded connections from the existing hidden units to the new candidate hidden unit are required to establish high-order nonlinearity in approximating the residual error, a PPLN approximates the high-order nonlinearity by using trainable parametric or semiparametric nonlinear smooth activations based on minimum mean squared error criterion. An analysis is provided to show that the maximum correlation training criterion used in a CCLN tends to produce hidden units that saturate and thus makes it more suitable for classification tasks instead of regression tasks as evidenced in the simulation results. It is also observed that this critical weakness in CCLN can also potentially carry over to classification tasks, such as the two-spiral benchmark used in the original CCLN paper.

关键词： Neurons Network topology Laboratories backpropagation algorithms Supervised learning Analytical models Multilayer perceptrons Biological neural networks Neural networks Multi-layer neural network

来源：评论

学校读者我要写书评

暂无评论

OPTIMAL UNSUPERVISED MOTOR LEARNING FOR DIMENSIONALITY REDUCTION OF NONLINEAR CONTROL-SYSTEMS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1994年第6期5卷 965-973页

作者： SANGER, TD NASA Jet Propulsion Laboratory Pasadena CA USA

In this paper, optimal unsupervised motor learning is defined to be a technique for finding the coordinate system of minimum dimensionality which can adequately describe a particular motor task. An explicit method is provided for learning a stable controller that translates commands within the new coordinate system into motor variables appropriate for plant control. The method makes use of previously described Neural Network algorithms including the Generalized Hebbian Algorithm [1], Basis-Function Trees [2], and Trajectory Extension Learning [3]. Examples of applications to a real direct-drive two joint planar robot arm and a simulated three joint robot arm with visual sensing are given.

关键词： Nonlinear control systems Control systems backpropagation algorithms Robot sensing systems Robot kinematics Unsupervised learning Sensor systems Bandwidth Neural networks Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Diagnosing failed distribution transformers using neural networks

引用

IEEE TRANSACTIONS ON POWER DELIVERY 2001年第4期16卷 631-636页

作者： Farag, AS Mohandes, M Al-Shaikh, A King Fahd Univ Petr & Minerals Dhahran 31261 Saudi Arabia SCECO E EDSD EED Dammam Saudi Arabia

An Artificial Neural Networks (ANN) system was developed for distribution transformer's failure diagnosis. The diagnosis was based on the latest standards and expert experiences in this field. The ANN was trained utilizing Back Propagation Algorithm using a real (out of the field) data obtained from utilities distribution networks transformer's failures. The ANN consists of six individual ANN according to six important factors used to give certain outputs. These factors are: the age of the transform, the weather condition, if there are any damaged bushings?, if there are any damaged casing or enclosure?, if there is oil leakage?, and if there are any faults in the windings?. The six ANNs are combined in one ANN to give all the outputs of the individual six ANNs. The developed ANN can be used to give recommended complete diagnosis for working transformers to avoid possible failures depending on their operating conditions. Good diagnosis accuracy is obtained. with the proposed approach applied and with the analysis of the attainable results.

关键词： backpropagation bushings distribution networks failure analysis fault diagnosis neural nets power engineering computing power transformer insulation power transformers transformer oil transformer windings ANN training backpropagation algorithm damaged bu ELECTRIC TRANSFORMERS Transformer windings backpropagation algorithms transformer oil transformer insulation back propagation Power engineering computing Fault diagnosis Power grids Neural network FAILURE ANALYSIS

来源：评论

学校读者我要写书评

暂无评论

LEARNING IN LINEAR NEURAL NETWORKS - A SURVEY

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第4期6卷 837-858页

作者： BALDI, PF HORNIK, K CALTECH DIV BIOLPASADENACA 91109 VIENNA TECH UNIV INST STAT & WAHRSCHEINLICHKEITSTHEORIEA-1040 VIENNAAUSTRIA

Networks of linear units are the simplest kind of networks, where the basic questions related to learning, generalization, and self-organization can sometimes be answered analytically, We survey most of the known results on linear networks, including: 1) backpropagation learning and the structure of the error function landscape, 2) the temporal evolution of generalization, and 3) unsupervised learning algorithms and their properties, The connections to classical statistical ideas, such as principal component analysis (PCA), are emphasized as well as several simple but challenging open questions, A few new results are also spread across the paper, including an analysis of the effect of noise on backpropagation networks and a unified view of all unsupervised algorithms.

关键词： Intelligent networks Neural networks Unsupervised learning backpropagation algorithms Principal component analysis Neurons Computer networks Evolution (biology) Algorithm design and analysis Biology computing

来源：评论

学校读者我要写书评

暂无评论

Fatigue response and constitutive behavior modeling of poly(ethylene terephthalate) unreinforced and nanocomposite fibers using genetic neural networks

引用

POLYMER COMPOSITES 2012年第12期33卷 2277-2287页

作者： Averett, Rodney D. Realff, Mary L. Jacob, Karl Georgia Inst Technol Sch Mat Sci & Engn Atlanta GA 30332 USA Georgia Inst Technol George W Woodruff Sch Mech Engn Atlanta GA 30332 USA

The constitutive behavior of poly(ethylene terephthalate) (PET) unreinforced (control) and PET fibers reinforced with 5 wt% vapor-grown carbon nanofibers (VGCNFs) under uniaxial tension and subsequent to fatigue loading has been evaluated utilizing various analytical models. Two types of fatigue tests were performed: (1) Long cycle fatigue at 50 Hz (glassy fatigue) to evaluate fatigue resistance and (2) fatigue at 5 Hz (rubbery fatigue) to evaluate residual strength performance. The long cycle fatigue results at 50 Hz indicated that the PET-VGCNF sample exhibited an increased fatigue resistance of almost two orders of magnitude when compared to the PET unreinforced filament. The results of the fatigue tests at 5 Hz indicated that the constitutive response of both the PET control and PET-VGCNF samples changed subsequent to fatigue loading. The large deformation uniaxial constitutive response of the PET and PET-VGCNF fibers was modeled utilizing genetic-algorithm (GA) based training neural networks. The results showed that the large deformation uniaxial tension constitutive behavior of both PET unreinforced and PET-VGCNF samples with and without prior fatigue can be represented with good accuracy utilizing neural networks trained via genetic-based backpropagation algorithms, once the appropriate post-fatigue constitutive behavior is utilized. Experimental data of uniaxial tensile tests and experimental postfatigue constitutive data have been implemented into the networks for adequate training. The fatigue tests were conducted under tension-tension fatigue conditions with variations in the stress ratio (R), maximum stress (smax), number of cycles (N), and the residual creep strain (eR). POLYM. COMPOS., 2012. (C) 2012 Society of Plastics Engineers

关键词： Hz Fatigue Neural network Fatigue tests Cycle fatigue FATIGUE RESISTANCE backpropagation algorithms role model Polyethylene Terephthalates Constitutive unreinforced

来源：评论

学校读者我要写书评

暂无评论

Optimization of HV electrode systems by neural networks using a new learning method

引用

IEEE TRANSACTIONS ON DIELECTRICS AND ELECTRICAL INSULATION 1996年第6期3卷 737-742页

作者： Mukherjee, PK Trinitis, C Steinbigler, H TECH UNIV MUNICH HIGH VOLTAGE INSTD-8000 MUNICHGERMANY

To avoid a large number of iterations, optimization of electrode shapes has been done by artificial neural networks (NN). Two practical examples have been considered, an axisymmetric single-phase GIS bus termination and an axisymmetric transformer shield ring. The shape of the electrodes has been taken as quarter-ellipse or half-ellipse because an ellipse has more flexibility a than circle. For NN, the socalled resilient propagation algorithm, learning faster than the standard back-propagation algorithm, has been employed. The training sets as well as the test sets of NN have been prepared by charge simulation method.

关键词： Optimization methods Electrodes Neural networks Learning systems Neurons Artificial neural networks Shape Computational modeling backpropagation algorithms Power transformer insulation

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：