检索结果-内蒙古大学图书馆

Overview of fuzzified neural networks with comparison of learning mechanism

INTERNATIONAL JOURNAL OF FUZZY SYSTEMS 2008年第2期10卷 71-83页

作者： Kuo, Ching-Yi Wang, Hsiao-Fan Natl Tsing Hua Univ Dept Ind Engn & Engn Management Hsinchu 300 Taiwan

A fuzzified neural network copes with fuzzy signals and/or weights so that the information about the uncertainty of input and output can be served in the training process. Since learning process is the main function of fuzzy neural networks, in this study, we focus on review and comparison of the existing learning algorithms, so that the theoretical achievement and the application agenda of each considered algorithm can be clarified from the aspects of computation complexity and accuracy. Two numerical examples of nonlinear mapping of fuzzy numbers and realization of fuzzy IF-THEN rules are used for illustration and analysis.

关键词： fuzzy neural networks fuzzy arithmetic learning algorithm back-propagation

来源：评论

学校读者我要写书评

暂无评论

An application of an associative learning model to a Morris pool with a single landmark

引用

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2008年第1期56卷 212-217页

作者： Grau-Sanchez, M. Noguera, M. Diaz-Barrero, J. L. Chamizo, V. D. Rodrigo, T. Tech Univ Catalonia Dept Appl Math 2 Barcelona 08034 Spain Tech Univ Catalonia Dept Appl Math 3 Barcelona 08034 Spain Univ Barcelona Dept Basic Psychol Barcelona 08035 Spain

A simplified model that studies stimuli representation and the set of algorithms that let us analyze associative learning in some particular cases with predetermined values of the salience of the stimuli is presented. We simulate an experiment where rats were trained in a Morris pool to find a hidden platform in the presence of a single landmark. The results obtained agree with a previous study where it was found that the control acquired by a single landmark is different depending on its relative distance from the hidden platform. In this paper, some simplified equations of the associative learning model have been used. (C) 2008 Elsevier Ltd. All rights reserved.

关键词： learning algorithm associative learning McLaren model saliences latencies

来源：评论

学校读者我要写书评

暂无评论

A learning rule for very simple universal approximators consisting of a single layer of perceptrons

引用

NEURAL NETWORKS 2008年第5期21卷 786-795页

作者： Auer, Peter Burgsteiner, Harald Maass, Wolfgang Graz Univ Appl Sci Dept Hlth Care Engn A-8020 Graz Austria Univ Min & Met Leoben Chair Informat Technol A-8700 Leoben Austria Graz Univ Technol Inst Theoret Comp Sci A-8010 Graz Austria

One may argue that the simplest type of neural networks beyond a single perceptron is an array of several perceptrons in parallel. In spite of their simplicity, Such circuits can compute any Boolean function if one views the majority of the binary perceptron outputs as the binary Output Of the parallel perceptron, and they are universal approximators for arbitrary continuous functions With values in 10, 11 if one views the fraction of perceptrons that Output I as the analog output of the parallel perceptron. Note that in contrast to the familiar model of a "multi-layer perceptron" the parallel perceptron that we consider here has just binary values as outputs of gates on the hidden layer. For a long time one has thought that there exists no competitive learning algorithm for these extremely simple neural networks, which also came to be known as committee machines. It is commonly assumed that one has to replace the hard threshold gates on the hidden layer by sigmoidal gates (or RBF-gates) and that one has to tune the weights on at least two successive layers in order to achieve satisfactory learning results for any class of neural networks that yield universal approximators. We show that this assumption is not true, by exhibiting a simple learning algorithm for parallel perceptrons - the parallel delta ride (p-delta rule). In contrast to backprop for multi-layer perceptrons, the p-delta rule only has to tune a single layer of weights, and it does not require the computation and Communication of analog values with high precision. Reduced communication also distinguishes our new learning rule from other learning rules for parallel perceptrons Such as MADALINE. Obviously these features make the p-delta rule attractive as a biologically more realistic alternative to backprop in biological neural circuits, but also for implementations in special purpose hardware. We show that the p-delta rule also implements gradient descent - with regard to a suitable error measure - alt

关键词： learning algorithm parallel delta rule parallel perceptrons committee machines reduced communication

来源：评论

学校读者我要写书评

暂无评论

Time series prediction using wavelet process neural network

引用

Chinese Physics B 2008年第6期17卷 1998-2003页

作者：丁刚钟诗胜李洋 School of Mechatronics Engineering Harbin Institute of Technology

In the real world, the inputs of many complicated systems are time-varying functions or processes. In order to predict the outputs of these systems with high speed and accuracy, this paper proposes a time series prediction model based on the wavelet process neural network, and develops the corresponding learning algorithm based on the expansion of the orthogonal basis functions. The effectiveness of the proposed time series prediction model and its learning algorithm is proved by the Macke-Glass time series prediction, and the comparative prediction results indicate that the proposed time series prediction model based on the wavelet process neural network seems to perform well and appears suitable for using as a good tool to predict the highly complex nonlinear time series.

关键词： time series prediction wavelet process neural network learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Machine-part cell formation in group technology using a modified ART1 method

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2008年第1期188卷 140-152页

作者： Yang, Miin-Shen Yang, Jenn-Hwai Chung Yuan Christian Univ Dept Appl Math Chungli 32023 Taiwan

Group Technology (GT) is a useful way of increasing the productivity for manufacturing high quality products and improving the flexibility of manufacturing systems. Cell formation (CF) is a key step in GT. It is used in designing good cellular manufacturing systems using the similarities between parts in relation to the machines in their manufacture. It can identify part families and machine groups. Recently, neural networks (NNs) have been widely applied in GT due to their robust and adaptive nature. NNs are very suitable in CF with a wide variety of real applications. Although Dagli and Huggahalli adopted the ART1 network with an application in machine-part CF, there are still several drawbacks to this approach. To address these concerns, we propose a modified ART1 neural learning algorithm. In our modified ART1, the vigilance parameter can be simply estimated by the data so that it is more efficient and reliable than Dagli and Huggahalli's method for selecting a vigilance value. We then apply the proposed algorithm to machine-part CF in GT. Several examples are presented to illustrate its efficiency. In comparison with Dagli and Huggahalli's method based on the performance measure proposed by Chandrasekaran and Rajagopalan, our modified ART1 neural learning algorithm provides better results. Overall, the proposed algorithm is vigilance parameter-free and very efficient to use in CF with a wide variety of machine/part matrices. (C) 2007 Elsevier B.V. All rights reserved.

关键词： group technology cell formation ART1 neural network learning algorithm group efficiency

来源：评论

学校读者我要写书评

暂无评论

Artificial Immune Networks: Models and Applications

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2008年第2期1卷 168-176页

作者： Shen, Xian Gao, X. Z. Bie, Rongfang Beijing Normal Univ Coll Informat Sci & Technol Beijing 100875 Peoples R China Aalto Univ Dept Elect Engn FI-02150 Espoo Finland

Artificial Immune Systems (AIS), which is inspired by the nature immune system, has been applied for solving complex computational problems in classification, pattern recognition, and optimization. In this paper, the theory of the natural immune system is first briefly introduced. Next, we compare some well-known AIS and their applications. Several representative artificial immune networks models are also discussed. Moreover, we demonstrate the applications of artificial immune networks in various engineering fields.

关键词： natural immune systems artificial immune systems artificial immune networks learning algorithm data mining

来源：评论

学校读者我要写书评

暂无评论

Performance prediction of a ground-coupled heat pump system using artificial neural networks

引用

EXPERT SYSTEMS WITH APPLICATIONS 2008年第4期35卷 1940-1948页

作者： Esen, Hikmet Inalli, Mustafa Sengur, Abdulkadir Esen, Mehmet Firat Univ Fac Tech Educ Dept Mech Educ TR-23119 Elazig Turkey Firat Univ Fac Engn Dept Mech Engn TR-23279 Elazig Turkey Firat Univ Fac Tech Educ Dept Elect & Comp Sci TR-23119 Elazig Turkey

This paper describes the applicability of artificial neural networks (ANNs) to predict performance of a horizontal ground-coupled heat pump (GCHP) system. Performance forecasting is the precondition for the optimal control and energy saving operation of heat pump systems. ANNs have been used in varied applications and they have been shown to be particularly useful in system modelling and system identification. In order to train the ANN, limited experimental measurements were used as training data and test data. In this study, in input layer, there are air temperature entering condenser unit and air temperature leaving condenser unit, and ground temperatures (I and 2 in);coefficient of performance of system (COPS) is in output layer. The back propagation learning algorithm with three different variants, namely Levenberg-Marguardt (LM), Pola-Ribiere conjugate gradient (CGP), and scaled conjugate gradient (SCG), and tangent sigmoid transfer function were used in the network so that the best approach can find. The most suitable algorithm and neuron number in the hidden layer are found as LM with seven neurons. For this number level, after the training, it is found that Root-mean squared (RMS) value is 1%, and absolute fraction of variance (R-2) value is 99.999% and coefficient of variation in percent (COV) value is 28.62%. It is concluded that, ANNs can be used for prediction of COPS as an accurate method in the systems. (C) 2007 Elsevier Ltd. All rights reserved.

关键词： artificial neural network learning algorithm ground-coupled heat pump horizontal heat exchanger coefficient of performance

来源：评论

学校读者我要写书评

暂无评论

Synchronized Interactions in Spiked Neuronal Networks

引用

COMPUTER JOURNAL 2008年第6期51卷 723-730页

作者： Gelenbe, Erol Timotheou, Stelios Univ London Imperial Coll Sci Technol & Med Dept Elect & Elect Engn Intelligent Syst & Networks Grp London SW7 2BT England

The study of artificial neural networks has originally been inspired by neurophysiology and cognitive science. It has resulted in a rich and diverse methodology and in numerous applications to machine intelligence, computer vision, pattern recognition and other applications. The random neural network (RNN) is a probabilistic model which was inspired by the spiking behaviour of neurons, and which has an elegant mathematical treatment that provides both its steady-state behaviour and offers efficient learning algorithms for recurrent networks. Second-order interactions, where more than one neuron jointly act upon other cells, have been observed in nature;they generalize the binary (excitatory-inhibitory) interaction between pairs of cells and give rise to synchronous firing (SF) by many cells. In this paper, we develop an extension of the RNN to the case of synchronous interactions, which are based on two cells that jointly excite a third cell;this local behaviour is in fact sufficient to create SF by large ensembles of cells. We describe the system state and derive its stationary solution as well as a O(N-3) gradient descent learning algorithm for a recurrent network with N cells when both standard excitatory-inhibitory interactions, as well as SF, are present.

关键词： random neural network synchronized interactions learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A new boosting algorithm for improved time-series forecasting with recurrent neural networks

引用

INFORMATION FUSION 2008年第1期9卷 41-55页

作者： Assaad, Mohammad Bone, Romuald Cardot, Hubert Univ Tours Lab Informat F-37200 Tours France

Ensemble methods for classification and regression have focused a great deal of attention in recent years. They have shown, both theoretically and empirically, that they are able to perform substantially better than single models in a wide range of tasks. We have adapted an ensemble method to the problem of predicting future values of time series using recurrent neural networks (RNNs) as base learners. The improvement is made by combining a large number of RNNs, each of which is generated by training on a different set of examples. This algorithm is based on the boosting algorithm where difficult points of the time series are concentrated on during the learning process however, unlike the original algorithm, we introduce a new parameter for tuning the boosting influence on available examples. We test our boosting algorithm for RNNs on single-step-ahead and multi-step-ahead prediction problems. The results are then compared to other regression methods, including those of different local approaches. The overall results obtained through our ensemble method are more accurate than those obtained through the standard method, backpropagation through time, on these datasets and perform significantly better even when long-range dependencies play an important role. (C) 2006 Elsevier B.V. All rights reserved.

关键词： learning algorithm boosting recurrent neural networks time series forecasting multi-step-ahead prediction

来源：评论

学校读者我要写书评

暂无评论

Population heterogeneity and color stimulus heterogeneity in agent-based color categorization

引用

JOURNAL OF THEORETICAL BIOLOGY 2008年第4期253卷 680-700页

作者： Komarova, Natalia I. Jameson, Kimberly A. Univ Calif Irvine Dept Math Inst Math Behav Sci Irvine CA 92717 USA

Investigating the interactions between universal and culturally specific influences on color categorization across individuals and cultures has proven to be a challenge for human color categorization and naming research. The present article simulates the evolution of color lexicons to evaluate the role of two realistic constraints found in the human phenomenon: (i) heterogeneous observer populations and (ii) heterogeneous color stimuli. Such constraints, idealized and implemented as agent categorization and communication games, produce interesting and unexpected consequences for stable categorization solutions evolved and shared by agent populations. We find that the presence of a small fraction of color deficient agents in a population, or the presence of a "region of increased salience" in the color stimulus space, break rotational symmetry in population categorization solutions, and confine color category boundaries to a subset of available locations. Further, these heterogeneities, each in a different, predictable, way, might lead to a change of category number and size. In addition, the concurrent presence of both types of heterogeneity gives rise to novel constrained solutions which optimize the success rate of categorization and communication games. Implications of these agent-based results for psychological theories of color categorization and the evolution of color naming systems in human societies are discussed. (C) 2008 Elsevier Ltd. All rights reserved.

关键词： evolutionary game theory dichromat color naming population inhomogeneity environmental color distributions discrimination-similarity game learning algorithm

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：