检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： J.J. Steil Neuroinformatics Group Faculty of Technology University of Bielefeld Germany

We introduce a new learning rule for fully recurrent neural networks which we call backpropagation-decorrelation rule (BPDC). It combines important principles: one-step backpropagation of errors and the usage of temporal memory in the network dynamics by means of decorrelation of activations. The BPDC rule is derived and theoretically justified from regarding learning as a constraint optimization problem and applies uniformly in discrete and continuous time. It is very easy to implement, and has a minimal complexity of 2N multiplications per time-step in the single output case. Nevertheless we obtain fast tracking and excellent performance in some benchmark problems including the Mackey-Glass time-series.

关键词： Decorrelation Reservoirs backpropagation algorithms Recurrent neural networks Biological system modeling Neurons Constraint optimization Speech recognition Adaptive control Information processing

来源：评论

学校读者我要写书评

暂无评论

Softprop: softmax neural network backpropagation learning

Softprop: softmax neural network backpropagation learning

引用

International Joint Conference on Neural Networks (IJCNN)

作者： M. Rimer T. Martinez Computer Science Department Brigham Young University Provo UT USA

Multi-layer backpropagation, like many learning algorithms that can create complex decision surfaces, is prone to overfitting. Softprop is a novel learning approach presented here that is reminiscent of the softmax explore-exploit Q-learning search heuristic. It fits the problem while delaying settling into error minima to achieve better generalization and more robust learning. This is accomplished by blending standard SSE optimization with lazy training, a new objective function well suited to learning classification tasks, to form a more stable learning model. Over several machine learning data sets, softprop reduces classification error by 17.1 percent and the variance in results by 38.6 percent over standard SSE minimization.

关键词： Neural networks Robustness Machine learning Computer science backpropagation algorithms Training data Delay Feedforward systems Multi-layer neural network Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

An alternative approach to solve convergence problems in the backpropagation algorithm

An alternative approach to solve convergence problems in the...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： A. Goedtel I. Nunes da Silva P.J.A. Semi Department of Electrical Engineering State University of São Paulo Sao Paulo Brazil

The multilayer perceptron network has become one of the most used in the solution of a wide variety of problems. The training process is based on the supervised method, where the inputs are presented to the neural network and the output is compared with a desired value. However, the algorithm presents convergence problems when the desired output of the network has small slope in the discrete time samples or the output is a quasi-constant value. The proposal of this paper is presenting an alternative approach to solve this convergence problem with a pre-conditioning method of the desired output data set before the training process and a post-conditioning when the generalization results are obtained. Simulations results are presented in order to validate the proposed approach.

关键词： Convergence backpropagation algorithms Multilayer perceptrons Neural networks Proposals Least squares methods Frequency division multiplexing Learning automata Encoding Blind equalizers

来源：评论

学校读者我要写书评

暂无评论

Diagonal recurrent neural networks for a walking robot

引用

Journal of information and optimization sciences 2004年第1期25卷 35-51页

作者： Kuei-Shu Hsu Hung-Shiang Chuang Department of Automation Engineering Kao Yuan Institute of Technology Lu-Chu Hsiang Kaohsiung Hsien Taiwan 821 R.O.C.

Whilst the necessity of finding an intelligent-based controlling method for a two-leg walking robot increases, the balance of the under-actuated leg consisting of two links is emphasized in this study. This is not only a nonlinear structure, but also a single-input double-output system. However, the problem becomes concrete through the proposed diagonal recurrent neural networks (DRNN) method. In this paper, two kinds of DRNN are introduced into the control system. The diagonal recurrent neuroidentifier (DRNI) is selected as an identifier, and the diagonal recurrent neurocontroller (DRNC) is determined as a controller. Additionally, a generalized dynamic backpropagation algorithm (DBP) is also applied to train both DRNC and DRNI. With the simulated results, it is shown that the under-actuated leg is balanced and stabilized by DRNN. This study definitely contributes the intelligent-based as well as the real-time controlled method for a two-leg walking robot with profound insight.

关键词： recurrent neural networks walking robot dynamic backpropagation algorithm backpropagation algorithms walking robots recurrent neural nets diagonal recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Adaptive discrete - time sliding mode control using recurrent neural identifier

引用

IFAC Proceedings Volumes 2004年第21期37卷 735-740页

作者： Ieroham S. Baruch P. Luis-Alberto Hernandez Josefina Barrera-Cortes CINVESTAV-IPN Dept. of Automatic Control Ave. IPN No 2508 A.P. 14-470 07360 Mexico D.F. MEXICO CINVESTAV-IPN Dept. of Biotechnology and Bioengineering Ave. IPN No 2508 A.P. 14-470 07360 Mexico D.F. MEXICO

A new adaptive control system containing a Recurrent Neural Network (RNN) identifier and a Sliding Mode Controller (SMC) is proposed. The SMC is derived defining the sliding surface with respect to the output tracking error. The necessary state and parameter information to resolve the SMC is obtained from a RNN identifier, which gives the needed flexibility when the plant parameters changed. The good quality of the proposed control scheme is illustrated by simulation results, obtained with a fed-batch fermentation plant model.

关键词： sliding mode control discrete-time systems adaptive control neural network models backpropagation algorithms identification state estimation biotechnology fed-batch fermentation plant model

来源：评论

学校读者我要写书评

暂无评论

Performance studies on KBANN

Performance studies on KBANN

引用

International Conference on Hybrid Intelligent Systems (HIS)

作者： R.P. Bose G. Nagaraja Applied Research Group Satyam Computer Services Limited Bangalore India Department of Computer Science and Engineering Indian Institute of Technology Bombay Mumbai India

Hybrid models combining the analytical (rule-based) and connectionist (artificial neural network (ANN)) paradigms are called knowledge based neural networks (KBNN). The knowledge based artificial neural network (KBANN) is one such model that makes use of the domain theory represented as propositional rules and training examples. In this article, we analyze the performance of KBANN and suggest some ideas of improving its capabilities. A study on the effect of inductive bias on KBANN, use of adaptive learning algorithms instead of the standard backpropagation to improve the training times and the use of regularization methods for improving generalization performance is presented. It is shown that for better performance, the initial weight assignment to links obtained by domain theory varies with the domain and the performance of KBANN is improved by using regularization methods like the weight decay along with Rprop training algorithm instead of the standard backpropagation.

关键词： Artificial neural networks Machine learning backpropagation algorithms Analytical models Performance analysis Machine learning algorithms Learning systems Computer networks Computer science Knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

Daily peak temperature forecasting with Elman neural networks

Daily peak temperature forecasting with Elman neural network...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： S. Vitabile M. Pernice S. Gaglio Lstituto di CAlcolo e Reti ad alte prestazioni (ICAR) Italian National Council of Research Palermo Italy Istituto di CAlcolo e Reti Italian National Research Council Palermo ITALY Dipartimento di Ingegneria Informatica University of Palermo Palermo ITALY

This work presents a forecaster based on an Elman artificial neural network trained with resilient backpropagation algorithm for predicting the daily peak temperatures one day ahead. The available time series was recorded at Petrosino (TP), in the west coast of Sicily, Italy and it is composed by temperature (min and max values), the humidity (min and max values) and the rainfall value between January 1st, 1995 and May 14th, 2003. Performances and reliabilities of the proposed model were evaluated by a number of measures, comparing different neural models. Experimental results show very good prediction performances.

关键词： Temperature Neural networks Weather forecasting Electronic mail Artificial neural networks backpropagation algorithms Load forecasting Predictive models Performance evaluation Computer networks

来源：评论

学校读者我要写书评

暂无评论

Neural-fuzzy approach for content-based retrieval of digital video

Neural-fuzzy approach for content-based retrieval of digital...

引用

Canadian Conference on Electrical and Computer Engineering (CCECE)

作者： S. Kulkarni Department of Computer Science and Mathematics Nipissing University North Bay ONT Canada

As digital video databases become more and more pervasive, finding video in large databases becomes a major problem. Because of the nature of video (streamed objects), accessing the content of such databases is inherently a time-consuming operation. The paper proposes a novel neural-fuzzy based approach for retrieving a specific video clip from a video database. Fuzzy logic is used for expressing queries in terms of natural language and a neural network is designed to learn the meaning of these queries. The queries are designed based on features such as colour and texture of shots, scenes and objects in video clips. An error backpropagation algorithm is proposed to learn the meaning of queries in fuzzy terms such as "very similar", "similar" and "some-what similar". Preliminary experiments were conducted on a small video database and different combinations of queries using colour and texture features along with a visual video clip; very promising results were achieved.

关键词： Content based retrieval Spatial databases Streaming media Information retrieval Fuzzy logic Natural languages Neural networks Layout backpropagation algorithms Visual databases

来源：评论

学校读者我要写书评

暂无评论

Fuzzy neural network classification design using support vector machine

Fuzzy neural network classification design using support vec...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Chin-Teng Lin Chang-Moun Yeh Chun-Fei Hsu Department of Electrical and Control Engineering National Chiao Tung University Hsinchu Taiwan

ISBN: (纸本)078038251X

Fuzzy neural networks (FNNs) for pattern classification usually use the backpropagation or C-cluster type learning algorithms to learn the parameters of the fuzzy rules and membership functions from the training data. However, such kinds of learning algorithms usually cannot minimize the empirical risk (training error) and expected risk (testing error) simultaneously, and thus cannot reach a good classification performance in the testing phase. To tackle this drawback, a support-vector-based fuzzy neural network classification (SVFNNC) is proposed. The SVFNNC combines the superior classification power of support vector machine (SVM) in high reasoning of FNN in handling uncertainty information. The learning algorithm consists of two learning phases. In the phase 1, the fuzzy rules and membership functions are automatically determined by the clustering principle. In the phase 2, the parameters of FNN are calculated by the SVM with the proposed adaptive fuzzy kernel function. To investigate the effectiveness of the proposed SVFNNC, it is applied to the iris, vehicle and dna datasets. Experimental results show that the proposed SVFNNC can achieve good classification performance with drastically reduced number of fuzzy kernel functions.

关键词： Fuzzy neural networks Support vector machines Support vector machine classification backpropagation algorithms Testing Kernel Pattern classification Training data Uncertainty Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning multiple correct classifications from incomplete data using weakened implicit negatives

Learning multiple correct classifications from incomplete da...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： S. Whiting D. Ventura Department of Computer Science Brigham Young University Provo UT USA

Classification problems with output class overlap create problems for standard neural network approaches. We present a modification of a simple feedforward neural network that is capable of learning problems with output overlap, including problems exhibiting hierarchical class structures in the output. Our method of applying weakened implicit negatives to address overlap and ambiguity allows the algorithm to learn a large portion of the hierarchical structure from very incomplete data. Our results show an improvement of approximately 58% over a standard backpropagation network on the hierarchical problem.

关键词： Neural networks backpropagation algorithms Uncertainty Computer science Feedforward neural networks Labeling Filters Decision making Natural languages Equations

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：