检索结果-内蒙古大学图书馆

7th Brazilian Symposium on Neural Networks (SBRN 02)

作者： Rosa, JLG Pontificia Univ Catolica Campinas Mestrado Sistemas Computacao Mestrado Informat UniSantos BR-13012970 Campinas SP Brazil

ISBN: (纸本)0769517099

Nowadays artificial neural network models often lack many physiological properties of the nervous cell. Feedforward multilayer perceptron architectures, and even simple recurrent networks, still in vogue, are far from those encountered in cerebral cortex. Current learning algorithms are more oriented to computational performance than to biological credibility. The aim of this paper is to propose an artificial neural network system, called Bio-thetaR, including architecture and algorithm, to take care of a natural language processing problem, the thematic relationship, in a biologically inspired connectionist approach. Instead of feedforward or simple recurrent network, it is presented a bi-directional architecture. Instead of the well-known biologically implausible backpropagation algorithm, a neurophysiologically motivated one is employed to account for linguistic thematic role assignment in natural language sentences. In addition, several features concerning biological plausibility are also included.

关键词： Artificial neural networks backpropagation algorithms Bidirectional control Biological system modeling Biology computing Computer architecture Mathematical model Natural language processing Natural languages Psychology

来源：评论

学校读者我要写书评

暂无评论

A study of crossvalidation and bootstrap as objective functions for genetic algorithms 7

A study of crossvalidation and bootstrap as objective functi...

引用

7th Brazilian Symposium on Neural Networks

作者： de Lacerda, EGM de Carvalho, ACPLF Ludermir, TB Univ Fed Pernambuco Ctr Informat Recife PE Brazil

ISBN: (纸本)0769517099

This article addresses the problem of finding the adjustable parameters of a learning algorithm using Genetic algorithms. This problem is also known as the model selection problem. Some model selection techniques (e.g., cross-validation and bootstrap) are combined with the Genetic algorithms of different ways. Those combinations explore features of the Genetics algorithms such as the ability for handling multiple and noise objective functions.

关键词： Artificial intelligence backpropagation algorithms Character generation Genetic algorithms Humans Informatics Learning systems Machine learning algorithms Neural networks Thumb

来源：评论

学校读者我要写书评

暂无评论

Technique to design MLP networks in CMOS technology with adjustment of the backpropagation algorithm

Technique to design MLP networks in CMOS technology with adj...

引用

Brazilian Symposium on Neural Networks

作者： Fd.A. Pereira J.J.F. Cerqueira Departamento de Engenharia Elétrica da UFBA Salvador BA Brazil

The implementation of CMOS multipliers have been based on the use of either analog circuits for continuous time signal processing or switched current techniques for discrete time processing, once current mode topologies have become a trend for IC designers in low voltage applications. In this work we perform an analysis of some techniques for implementing the basic building blocks in a neural network using the IC technology for analog signal processing. Even though we focus on the operation of MOS devices in the strong inversion region deep into saturation, some aspects of the synapses in the weak inversion region are also explained, which has been accomplished through the use of classical asymptotical models for the drain current.

关键词： CMOS technology Algorithm design and analysis backpropagation algorithms CMOS analog integrated circuits Analog integrated circuits CMOS process Analog circuits Signal processing algorithms Switching circuits Network topology

来源：评论

学校读者我要写书评

暂无评论

Exponentiated backpropagation algorithm for multilayer feedforward neural networks

Exponentiated backpropagation algorithm for multilayer feedf...

引用

International Conference on Neural Information Processing

作者： N. Srinivasan V. Ravichandran K.L. Chan J.R. Vidhya S. Ramakirishnan S.M. Krishnan Department of Electronics and Communication Engineering Sri Venkateswara College of Engineering Sriperumbudur India Department of Electronics and Communication Engineering Biomedical Engineering Research Centre School of Electrical and Electronics Engineering Nanyang Technological University Singapore Department of Mathematics and Computer Applications Sri Venkateswara College of Engineering Sriperumbudur India Department of Mathematics and Computer Applications Department of Information Technology Sri Venkateswara College of Engineering Sriperumbudur India

ISBN: (纸本)9810475241

The gradient descent backpropagation learning algorithm is based on minimizing the mean square error. An alternate approach to gradient descent is the exponentiated gradient descent algorithm which minimizes the relative entropy. Exponentiated gradient descent applied to backpropagation is proposed for a multilayer feedforward neural network. The learning rules for changing weights in the output layer as well the hidden layer neurons in the network are developed. Simulations were performed to explore the convergence and learning of the backpropagation algorithm with exponentiated gradient descent. Accuracy obtained with exponentiated gradient descent back propagation was comparable to the gradient descent back propagation while convergence was faster. The results show that exponentiated gradient descent can be extended to a multilayer feedforward neural network and used in pattern classification applications.

关键词： Multi-layer neural network backpropagation algorithms Neural networks Feedforward neural networks Neurons Biomedical engineering Feeds Mean square error methods Convergence Pattern classification

来源：评论

学校读者我要写书评

暂无评论

The realization of quantum complex-valued backpropagation neural network in pattern recognition problem

The realization of quantum complex-valued backpropagation ne...

引用

International Conference on Neural Information Processing

作者： J.L. Mitrpanont A. Srisuphab Department of Computer Science Mahidol University Bangkok Thailand

The paper presents the approach of the quantum complex-valued backpropagation neural network or QCBPN. The challenge of our research is the expected results from the development of the quantum neural network using complex-valued backpropagation learning algorithm to solve classification problems. The concept of QCBPN emerged from the quantum circuit neural network research and the complex-valued backpropagation algorithm. We found that complex value and the quantum states share some natural representation suitable for the parallel computation. The quantum circuit neural network provides a qubit-like neuron model based on quantum mechanics with quantum backpropagation-learning rule, while the complex-valued backpropagation algorithm modifies standard backpropagation algorithm to learn complex number pattern in a natural way. The quantum complex-valued neuron model and the QCBPN learning algorithm are described. Finally, the realization of the QCBPN is exploited with a simple pattern recognition problem.

关键词： Neural networks Intelligent networks Pattern recognition Quantum computing backpropagation algorithms Neurons Quantum mechanics Computer networks Circuits Concurrent computing

来源：评论

学校读者我要写书评

暂无评论

A backpropagation algorithm with adaptive learning rate and momentum coefficient

A backpropagation algorithm with adaptive learning rate and ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Chien-Cheng Yu Bin-Da Liu Department of Electrical Engineering National Cheng Kung University Tainan Taiwan

Slower convergence and longer training times are the disadvantages often mentioned when the conventional backpropagation (BP) algorithm are compared with other competing techniques. In addition, in the conventional BP algorithm, the learning rate is fixed and that it is uniform for all the weights in a layer. In this paper, we propose an efficient acceleration technique, the backpropagation with adaptive learning rate and momentum term, which is based on the conventional BP algorithm by employing an adaptive learning rate and momentum factor, where the learning rate and momentum rate are adjusted at each iteration to reduce the training time. Simulation results indicate a superior convergence speed as compared to other competing methods.

关键词： backpropagation algorithms Convergence Acceleration Multilayer perceptrons Pattern classification Image processing Benchmark testing Jacobian matrices Error correction Optimization methods

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

Conference of the North American Fuzzy Information Processing Society - NAFIPS

作者： J.M. Adams K.S. Rattan Wright Stage University Dayton Ohio USA

A backpropagation learning method is developed 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： Fuzzy control Partitioning algorithms backpropagation algorithms Fuzzy logic Inference algorithms Robots Marine vehicles Learning systems Standards development Aerospace industry

来源：评论

学校读者我要写书评

暂无评论

backpropagation based training algorithm for Takagi-Sugeno type MIMO neuro-fuzzy network to forecast electrical load time series

Backpropagation based training algorithm for Takagi-Sugeno t...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： A.K. Palit G. Doeding W. Anheier D. Popovic Deneg GmbH Bremen Germany University of Brethemen Bremen Germany

Describes a backpropagation based algorithm that can be used to train the Takagi-Sugeno (TS) type multi-input multi-output (MIMO) neuro-fuzzy network efficiently. The training algorithm is efficient in the sense that it can bring the performance index of the network, such as the sum squared error (SSE), down to the desired error goal much faster than that the simple backpropagation algorithm (BPA). Finally, the above training algorithm is tested on neuro-fuzzy modeling and forecasting application of electrical load time series.

关键词： backpropagation algorithms MIMO Fuzzy neural networks Fuzzy logic Takagi-Sugeno model Load forecasting Predictive models Noise measurement Neural networks Electronic mail

来源：评论

学校读者我要写书评

暂无评论

A new three-term backpropagation algorithm with convergence analysis

A new three-term backpropagation algorithm with convergence ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Y.H. Zweiri J.F. Whidborne K. Althoefer L.D. Seneviratne Department of Mechanical Engineering King''s College London UK

The backpropagation (BP) algorithm is commonly used in many applications, including robotics, automation and weight changes of artificial neural networks (ANNs). This paper proposes the addition of an extra term, a proportional factor (PF), to the standard BP algorithm to speed up the weight adjusting process. The proposed algorithm is tested and the results show that the proposed algorithm outperforms the conventional BP algorithm in convergence speed and the ability to escape from learning stalls. The paper presents a convergence analysis of the three-term BP algorithm. It is shown that if the learning parameters of the three-term BP algorithm satisfies certain conditions given in this paper, then it is guaranteed that the system is stable and will converge to a local minimum. The paper shows that all the local minima of the cost function are stable for the three-term backpropagation algorithm.

关键词： backpropagation algorithms Convergence Algorithm design and analysis Artificial neural networks Robots Robotics and automation Extrapolation Acceleration Mechanical engineering Educational institutions

来源：评论

学校读者我要写书评

暂无评论

NEURO-FUZZY STRUCTURES IN FDI SYSTEM

引用

IFAC Proceedings Volumes 2002年第1期35卷 465-470页

作者： M.J.G.C. Mendes M. Kowal J. Korbicz J. M. G. Sá da Costa IDMEC/ISEL - Instituto Superior de Engenharia de Lisboa Polytechnic Institute of Lisbon Dept. of Mechanical Engineering Rua Conselheiro Emidio Navarro 1949-014 Lisboa Portugal fax:+351 21 8317057 University of Zielona Góra Institute of Control and Computation Engineering ul. Podgórna 50 65-246 Zielona Góra Poland fax:+4 8 68 3254615 Technical University of Lisbon Instituto Superior Técnico Dept. of Mechanical Engineering GCAR/IDMEC Av. Rovisco Pais1049-001 Lisboa Portugal fax:+351 21 8498097

Fault diagnosis systems have an important role in industrial plants because the early fault detection and isolation (FDI) can minimize damages in the plants. The main aim of this work is to propose a two-stage neuro-fuzzy approach as a fault diagnosis system in dynamic processes. The first stage of the system is responsible for fault detection and is implemented using a neuro-fuzzy (N-F) model. The second stage of the system is responsible for fault isolation and is built using an hierarchical structure of fuzzy neural networks. The FDI system is applied to fault diagnosis in the actuators of one sugar factory.

关键词： Fault diagnosis neural network fuzzy modelling backpropagation algorithms hierarchical structure actuators

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：