检索结果-内蒙古大学图书馆

Neural network modelling of Abbott-Firestone roughness parameters in honing processes

INTERNATIONAL JOURNAL OF SURFACE SCIENCE AND ENGINEERING 2017年第6期11卷 512-530页

作者： Sivatte-Adroer, Maurici Buj-Corral, Irene Llanas-Parra, Xavier Univ Politecn Cataluna Dept Mech Engn Sch Engn Vilanova I la Geltru EPSEVG Av Victor Balaguer 1 Barcelona 08800 Spain Univ Politecn Cataluna Dept Mech Engn Sch Engn Barcelona ETSEIB Av Diagonal 647 E-08028 Barcelona Spain Univ Politecn Cataluna Sch Engn Vilanova I la Geltru EPSEVG Automat Control Dept Av Victor Balaguer 1 Barcelona 08800 Spain

In present study, three roughness parameters defined in the Abbott-Firestone or bearing area curve, Rk, Rpk and Rvk, were modelled for rough honing processes by means of artificial neural networks (ANN). Input variables were grain size and density of abrasive, pressure of abrasive stones on the workpiece's surface, tangential or rotation speed of the workpiece and linear speed of the honing head. Two strategies were considered, either use of one network for modelling the three parameters at the same time or use of three networks, one for each parameter. Overall best neural network consists of three networks, one for each roughness parameter, with one hidden layer having 25, nine and five neurons for Rk, Rpk and Rvk respectively. However, use of one network for the three roughness parameters would allow addressing an indirect model. In this case, best solution corresponds to two hidden layers having 26 and 11 neurons.

关键词： surface roughness honing artificial neural networks ANN backpropagation algorithm Abbott-Firestone roughness parameters back propagation algorithm grain size density of abrasive linear speed tangential speed pressure

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Entropy Based Neuro-Wavelet Identifier-Cum-Quantifier for Discrimination of Gases/Odors

引用

IEEE SENSORS JOURNAL 2011年第7期11卷 1548-1555页

作者： Kumar, Ravi Das, R. R. Mishra, V. N. Dwivedi, R. Banaras Hindu Univ Inst Technol Dept Elect Engn Varanasi 221005 Uttar Pradesh India

In this paper, a new approach to design of an odor/gas identifier-cum-quantifier is presented. Dynamic response curves of an oxygen-plasma treated thick-film tin oxide sensor array exposed to four different gases were subjected to continuous wavelet transform (CWT). Appropriate wavelet coefficients were selected using multiscale principal component analysis (MSPCA). Fuzzy entropy and fuzzy subsethood values were calculated for the individual odor/gas and for the particular concentration band of each odor/gas, respectively. The quantitative information was encoded in the fuzzy subsethood values of the particular concentration bands in the output feature space, whereas the fuzzy entropy values were used to normalize the training data set consisting of MSPCA selected wavelet coefficients. A feedforward neural network was trained with a backpropagation algorithm with the training data containing the wavelet coefficients normalized with fuzzy entropies of individual odors/gases. The target data set was made up of the fuzzy subsethood values of the particular concentration band. The proposed network achieved identification and quantification of odors/gases with a 100% success rate. Also, fuzzy entropy based normalization helped to achieve 100% identification/quantification with a reduced number of sensors in the array.

关键词： backpropagation algorithm fuzzy entropy multi-scale principal component analysis oxygen plasma tin oxide sensors wavelet transform

来源：评论

学校读者我要写书评

暂无评论

THE EFFECT OF WEIGHT PRECISION AND RANGE ON NEURAL-NETWORK CLASSIFIER PERFORMANCE

引用

NEUROCOMPUTING 1994年第5-6期6卷 541-549页

作者： YOO, H PIMMEL, RL UNIV ALABAMA TUSCALOOSAAL 35401 UNIV MISSOURI COLUMBIAMO 65201

This study investigates the precision and range requirements for weights in feed-forward neural network classifiers using backpropagation training with simulated signals where we could control the difficulty of the problem. We found that a precision of five bits and a range equal to four times the mean weight magnitude produced the same performance as continuous weights. However, we noted that the required precision and range depended strongly on the problem difficulty, the network complexity, and the relationship between these two factors. We also found that uniformly distributed discrete weights produced better performance than non-uniformly distributed ones.

关键词： PATTERN CLASSIFICATION DISCRETE WEIGHTS FEEDFORWARD NETWORKS backpropagation algorithm COMPANDING WEIGHTS

来源：评论

学校读者我要写书评

暂无评论

Fast training of multilayer perceptrons

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1997年第6期8卷 1314-1320页

作者： Verma, B Laboratory of Chromatography DEPg.Fac.Quimica Universidad Nacional Autonoma de Mexico Circuito interior Cd Universitaria/CP 04510 Mexico D.F.Mexico

Training a multilayer perceptron by an error backpropagation algorithm is slow and uncertain, This paper describes a new approach which is much faster and certain than error backpropagation, The proposed approach is based on combined iterative and direct solution methods, In this approach, we use an inverse transformation for linearization of nonlinear output activation functions, direct solution matrix methods for training the weights of the output layer;and gradient descent, the delta rule, and other proposed techniques for training the weights of the hidden layers, The approach has been implemented and tested on many problems, Experimental results, including training times and recognition accuracy, are given, Generally, the approach achieves accuracy as good as or better than perceptrons trained using error backpropagation, and the training process is much faster than the error backpropagation algorithm and also avoids local minima and paralysis.

关键词： artificial neural networks backpropagation algorithm local minima multilayer perceptrons supervised learning

来源：评论

学校读者我要写书评

暂无评论

The solutions of vibration control problems using artificial neural networks

引用

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS 2003年第5期340卷 307-325页

作者： Alli, H Uçar, A Demir, Y Firat Univ Fac Engn Dept Mech Engn Elazig Turkey Firat Univ Fac Engn Dept Elect & Elect Engn Elazig Turkey

This paper introduces an alternative method artificial neural networks (ANN) used to obtain numerical solutions of mathematical models of dynamic systems, represented by ordinary differential equations (ODEs) and partial differential equations (PDEs). The proposed trial solution of differential equations (DEs) consists of two parts: The initial and boundary conditions (BCs) should be satisfied by the first part. However, the second part is not affected from initial and BCs, but it only tries to satisfy DE. This part involves a feedforward ANN containing adjustable parameters (weight and bias). The proposed solution satisfying boundary and initial condition uses a feedforward ANN with one hidden layer varying the neuron number in the hidden layer according to complexity of the considered problem. The ANN having appropriate architecture has been trained with backpropagation algorithm using an adaptive learning rate to satisfy DE. Moreover, we have, first, developed the general formula for the numerical solutions of nth-order initial-value problems by using ANN. For numerical applications, the ODEs that are the mathematical models of linear and nonlinear mass-damper-spring systems and the second- and fourth-order PDEs that are the mathematical models of the control of longitudinal vibrations of rods and lateral vibrations of beams have been considered. Finally, the responses of the controlled and non-controlled systems have been obtained. The obtained results have been graphically presented and some conclusion remarks are given. (C) 2003 The Franklin Institute. Published by Elsevier Science Ltd. All rights reserved.

关键词： vibration control problems artificial neural networks backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

On fault tolerant training of feedforward neural networks

引用

NEURAL NETWORKS 1997年第3期10卷 539-553页

作者： Arad, BS ElAmawy, A LOUISIANA STATE UNIV DEPT ELECT & COMP ENGNBATON ROUGELA 70803

This paper presents an extensive study of fault tolerant training of feedforward artificial neural networks. We present several versions of a very robust training algorithm and report the results of their simulations. Our algorithm is shown to outperform all existing training algorithms in its ability to tolerate different fault types and larger number of hidden unit failures. We show that the generalization ability of the proposed algorithm is substantially better than that of the standard backpropagation algorithm and is comparable with that of other existing fault tolerant algorithms. The algorithm is based on the backpropagation algorithm with built-in measures for extensive fault tolerant training. A novel concept presented in this paper is that of training the network for fault types beyond the limits of the activation function. We demonstrate that training for such unrealistic fault types enables the network to be more tolerant to realistic fault types within the limits of the activation function. Further, tradeoffs between training time, enhanced fault tolerance, and generalization properties are studied. (C) 1997 Elsevier Science Ltd.

关键词： artificial neural network fault tolerant training efficiency generalization backpropagation algorithm feedforward network neuron failure fault types

来源：评论

学校读者我要写书评

暂无评论

Supervised learning in multilayer spiking neural networks with inner products of spike trains

引用

NEUROCOMPUTING 2017年 237卷 59-70页

作者： Lin, Xianghong Wang, Xiangwen Hao, Zhanjun Northwest Normal Univ Sch Comp Sci & Engn Lanzhou 730070 Peoples R China

Recent advances in neurosciences have revealed that neural information in the brain is encoded through precisely timed spike trains, not only through the neural firing rate. This paper presents a new supervised, multi-spike learning algorithm for multilayer spiking neural networks, which can implement the complex spatio-temporal pattern learning of spike trains. The proposed algorithm firstly defines inner product operators to mathematically describe and manipulate spike trains, and then solves the problems of error function construction and backpropagation among multiple output spikes during learning. The algorithm is successfully applied to different temporal tasks, such as learning sequences of spikes and nonlinear pattern classification problems. The experimental results show that the proposed algorithm has higher learning accuracy and efficiency than the Multi-ReSuMe learning algorithm. It is effective for solving complex spatio-temporal pattern learning problems. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Spiking neural networks Supervised learning Inner products of spike trains Multilayer feedforward network backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Complex Function Approximation Based on Multi-ANN Approach

引用

Journal of Systems Engineering and Electronics 1995年第2期6卷 22-31页

作者： Li Renhou & Gao Feng (Institute of Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, China) Institute of Systems Engineering Xi'an Jiaotong University Xi'an 710049 China

This paper presents a multi-ANN approximation approach to approximate complex non-linear function. Comparing with single-ANN methods the proposed approach improves and increases the approximation and generalization ability, and adaptability greatly in learning processes of networks. The simulation results have been shown that the method can be applied to the modeling and identification of complex dynamic control systems.

关键词： backpropagation algorithm Multilayer perception Complex function approximation Input space partitioning.

来源：评论

学校读者我要写书评

暂无评论

Convergence of Constant Step Stochastic Gradient Descent for Non-Smooth Non-Convex Functions

引用

SET-VALUED AND VARIATIONAL ANALYSIS 2022年第3期30卷 1117-1147页

作者： Bianchi, Pascal Hachem, Walid Schechtman, Sholom IP Paris Telecom Paris LTCI Paris France Univ Gustave Eiffel CNRS LIGM F-77454 Marne La Vallee France

This paper studies the asymptotic behavior of the constant step Stochastic Gradient Descent for the minimization of an unknown function, defined as the expectation of a non convex, non smooth, locally Lipschitz random function. As the gradient may not exist, it is replaced by a certain operator: a reasonable choice is to use an element of the Clarke subdifferential of the random function;another choice is the output of the celebrated backpropagation algorithm, which is popular amongst practioners, and whose properties have recently been studied by Bolte and Pauwels. Since the expectation of the chosen operator is not in general an element of the Clarke subdifferential of the mean function, it has been assumed in the literature that an oracle of the Clarke subdifferential of the mean function is available. As a first result, it is shown in this paper that such an oracle is not needed for almost all initialization points of the algorithm. Next, in the small step size regime, it is shown that the interpolated trajectory of the algorithm converges in probability (in the compact convergence sense) towards the set of solutions of a particular differential inclusion: the subgradient flow. Finally, viewing the iterates as a Markov chain whose transition kernel is indexed by the step size, it is shown that the invariant distribution of the kernel converge weakly to the set of invariant distribution of this differential inclusion as the step size tends to zero. These results show that when the step size is small, with large probability, the iterates eventually lie in a neighborhood of the critical points of the mean function.

关键词： Clarke subdifferential backpropagation algorithm Differential inclusions Non convex and non smooth optimization Stochastic approximation

来源：评论

学校读者我要写书评

暂无评论

Novel approaches to determine age and gender from dental x-ray images by using multiplayer perceptron neural networks and image processing techniques

引用

CHAOS SOLITONS & FRACTALS 2019年 120卷 127-138页

作者： Avuclu, Emre Basciftci, Fatih Aksaray Univ Dept Comp Technol & Comp Programming Aksaray Turkey Selcuk Univ Dept Comp Engn Technol Fac TR-42003 Selcuklu Konya Turkey

It may be necessary to determine the identity or gender of a person for any reason (disasters, inheritance etc.). In such cases, forensic medical institutions are asked for help. Forensic science institutions try to estimate the age of people's teeth and bones. In this study, a novel algorithm was developed to keep these predictions at the highest level and to obtain definite results. The data base of 162 different tooth classes is created manually. All image sizes are 150x150 pixels. First, image preprocessing techniques have been applied to teeth images. These preprocessing techniques were first applied to teeth images. After this process, the segmentation process of the teeth images was performed to extract the feature by novel segmentation algorithm. Segmentation can be done automatically and dynamically. Numerical data obtained as a result of feature extraction from dental images is presented as an inputs to Multi layer perceptron neural network. In application, feature reduction can be performed. Thanks to the originally developed algorithm, the highest success rates were obtained with the highest 99.9% (full segment) and 100% (notfull segment) classification. After classification, for many dental groups the age estimate is performed with zero error. Application was developed as a multidisciplinary study. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Age estimation backpropagation algorithm Multilayer perceptron Panoramic x-ray Image processing techniques

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：