检索结果-内蒙古大学图书馆

learning algorithm for pattern classification using cellular neural networks

ELECTRONICS LETTERS 2000年第23期36卷 1941-1943页

作者： Grassi, G Di Sciascio, E Univ Lecce Dipartimento Ingn Innovazione I-73100 Lecce Italy Politecn Bari Dipartimento Elettrotecn & Elettron I-70125 Bari Italy

A new learning algorithm for pattern classification using cellular neural networks is described. The authors show that patterns belonging to the training set as well as patterns outside it can be classified reliably using the proposed algorithm. Comparisons with well established classification techniques clearly highlight the performances of the approach developed herein.

关键词： learning (artificial intelligence) Neural nets training set pattern classification cellular neural nets learning in AI classification techniques Pattern recognition learning algorithm cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

An efficient feature extraction method with pseudo-Zernike moment in RBF neural network-based human face recognition system

引用

EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING 2003年第9期2003卷 890-901页

作者： Haddadnia, J Ahmadi, M Faez, K Tarbiat Moallem Univ Savzevar Dept Engn Khorasan 397 Iran Univ Windsor Dept Elect & Comp Engn Windsor ON N9B 3P4 Canada Amirkabir Univ Technol Dept Elect Engn Tehran 15914 Iran

This paper introduces a novel method for the recognition of human faces in digital images using a new feature extraction method that combines the global and local information in frontal view of facial images. Radial basis function (RBF) neural network with a hybrid learning algorithm (HLA) has been used as a classifier. The proposed feature extraction method includes human face localization derived from the shape information. An efficient distance measure as facial candidate threshold (FCT) is defined to distinguish between face and nonface images. Pseudo-Zernike moment invariant (PZMI) with an efficient method for selecting moment order has been used. A newly defined parameter named axis correction ratio (ACR) of images for disregarding irrelevant information of face images is introduced. In this paper, the effect of these parameters in disregarding irrelevant information in recognition rate improvement is studied. Also we evaluate the effect of orders of PZMI in recognition rate of the proposed technique as well as RBF neural network learning speed. Simulation results on the face database of Olivetti Research Laboratory (ORL) indicate that the proposed method for human face recognition yielded a recognition rate of 99.3%.

关键词： human face recognition face localization moment invariant pseudo-Zernike moment RBF neural network learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A new supervised learning algorithm for multilayered and interconnected neural networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2000年第1期11卷 36-46页

作者： Yamamoto, Y Nikiforuk, PN Tottori Univ Fac Engn Dept Informat & Knowledge Engn Tottori 6808552 Japan Univ Saskatchewan Coll Engn Dept Mech Engn Saskatoon SK S7N 5A9 Canada

A new learning algorithm is presented for supervised learning of multilayered and interconnected neural networks without using a gradient method. First, fictitious teacher signals for the outputs of each hidden unit are algebraically determined by an error backpropagation (EBP) method. Then, the weight parameters are determined by using an exponentially weighted least squares (EWLS) method. This is called the EBP-EWLS algorithm for a multilayered neural network, For an interconnected neural network, the mathematical description of the neural network is arranged in the form for which the EBP-EWLS algorithm can be applied, Simulation studies have verified the proposed technique.

关键词： error backpropagation exponentially weighted least squares method interconnected neural network learning algorithm multilayered neural network orthogonal projection supervised learning

来源：评论

学校读者我要写书评

暂无评论

Unstructured object recognition using morphological learning

引用

DEFENCE SCIENCE JOURNAL 2002年第3期52卷 261-275页

作者： Kar, S Chandran, S Bhabha Atom Res Ctr Bombay 400085 Maharashtra India Indian Inst Technol Bombay 400076 Maharashtra India

A technique of object recognition which can detect absence or presence of objects of interest without making explicit use of their underlying geometric structure is deemed suitable for many practical applications. In this work, a method of recognising unstructured objects has been presented, wherein several gray patterns are input as examples to a morphological rule-based learning algorithm. The output of the algorithm are the corresponding gray structuring elements capable of recognising patterns in query images. The learning is carried out offline before recognition of the queries. The technique has been tested to identify fuel pellet surface imperfections. Robustness wrt intensity, orientation, and shape variations of the query patterns is built into the method. Moreover, simplicity of the recognition process leading to reduced computational time makes the method attractive to solve many practical problems.

关键词： object recognition learning algorithm morphological learning unstructured object gray structuring element geometric structure surface imperfections

来源：评论

学校读者我要写书评

暂无评论

Dynamic self-organized learning for optimizing the complexity growth of radial basis function neural networks

Dynamic self-organized learning for optimizing the complexit...

引用

IEEE International Conference on Industrial Technology

作者： Arisariyawong, S Charoenseang, S Srinakharinwirot Univ Dept Mech Engn Fac Engn Ongkharak 26120 Nakornayok Thailand

ISBN: (纸本)0780376579

This paper proposes a framework of automatically exploring the optimal size of a radial basis function (RBF) neural network. A dynamic self-organized learning algorithm is presented to adapt the structure of the network. The algorithm generates a new hidden unit based on the steady state error of network and the nearest distance from input data to the center of hidden unit. Furthermore, it also detects and removes any insignificant contributing hidden units. For optimizing the complexity growth of RBF neural network, the growing and pruning are combined during adaptation of RBF neural network structure. The examples of nonlinear dynamical system modeling are presented to illustrate the performance of the proposed algorithm.

关键词： self-organized learning learning algorithm radial basis function networks function estimation convergence

来源：评论

学校读者我要写书评

暂无评论

On using extended statistical queries to avoid membership queries

引用

JOURNAL OF MACHINE learning RESEARCH 2002年第3期2卷 359-395页

作者： Bshouty, NH Feldman, V Technion Israel Inst Technol Dept Comp Sci IL-32000 Haifa Israel

The Kushilevitz-Mansour (KM) algorithm is an algorithm that finds all the "large" Fourier coefficients of a Boolean function. It is the main tool for learning decision trees and DNF expressions in the PAC model with respect to the uniform distribution. The algorithm requires access to the membership query (MQ) oracle. The access is often unavailable in learning applications and thus the KM algorithm cannot be used. We significantly weaken this requirement by producing an analogue of the KM algorithm that uses extended statistical queries (SQ) (SQs in which the expectation is taken with respect to a distribution given by a learning algorithm). We restrict a set of distributions that a learning algorithm may use for its statistical queries to be a set of product distributions with each bit being 1 with probability rho, 1/2 or 1 - rho for a constant 1/2 > rho > 0 (we denote the resulting model by SQ-D-rho). Our analogue finds all the "large" Fourier coefficients of degree lower than clog n (we call it the Bounded Sieve (BS)). We use BS to learn decision trees and by adapting Freund's boosting technique we give an algorithm that learns DNF in SQ-D-rho. An important property of the model is that its algorithms can be simulated by MQs with persistent noise. With some modifications BS can also be simulated by MQs with product attribute noise (i.e., for a query x oracle changes every bit of x with some constant probability and calculates the value of the target function at the resulting point) and classification noise. This implies learnability of decision trees and weak learnability of DNF with this non-trivial noise. In the second part of this paper we develop a characterization for learnability with these extended statistical queries. We show that our characterization when applied to SQ-Dp is tight in terms of learning parity functions. We extend the result given by Blum et al. by proving that there is a class learnable in the PAC model with random classification noise a

关键词： .denote boosting expectation decision trees learning algorithm uniform distribution PAC model Boolean function DNF KM algorithm large Fourier

来源：评论

学校读者我要写书评

暂无评论

Self-organising networks in modelling experimental data in software engineering

引用

IEE PROCEEDINGS-COMPUTERS AND DIGITAL TECHNIQUES 2002年第3期149卷 61-78页

作者： Oh, SK Pedrycz, W Park, HS Wonkwang Univ Sch Elect & Elect Engn Iksan 570749 Chonbuk South Korea Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 2G6 Canada Polish Acad Sci Syst Res Inst PL-01447 Warsaw Poland

Experimental Software datasets describing Software projects in terms of their complexity and development time have been the subject of intensive modelling. A number of various modelling methodologies and detailed modelling designs hake been proposed including neural networks and fuzzy models. The authors introduce self-organising networks (SON) that result from a synergy of fuzzy inference schemes and polynomial neural networks (PNNs). The latter has included an efficient scheme of selecting input variables of the model being realised on a basis of a group method of data handling (GMDH) algorithm. The authors discuss a detailed architecture of the SON and propose a comprehensive learning algorithm. It is shown that this network exhibits a dynamic structure as the number of its layers as well as the number of nodes in each layer of the SON are not predetermined (as is the case in a popular topology of a multilayer perceptron). The experimental results include well-known software data such as the one describing software modules of the medical imaging system (MIS) and the NASA data set concerning software cost estimation. The experimental results reveal that the proposed model exhibits high accuracy.

关键词： learning in AI polynomial neural networks neural networks Neural nets Knowledge engineering techniques software engineering fuzzy inference schemes medical imaging system fuzzy logic experimental data modelling self-organising networks performance index group method of data handling algorithm learning (artificial intelligence) fuzzy models Formal logic self-organising feature maps learning algorithm Software engineering techniques experimental software datasets

来源：评论

学校读者我要写书评

暂无评论

Neural network approximation to nonlinear dynamics by Velocity Error Backpropagation

引用

ELECTRICAL ENGINEERING IN JAPAN 2002年第2期140卷 26-35页

作者： Ishii, H Aiyoshi, E Keio Univ Dept Appl Phys & Physico Informat Fac Sci & Technol Tokyo 108 Japan

This paper presents a new type of recurrent neural network (RNN) and its teaming algorithm for nonlinear dynamics, called "Velocity-Error Backpropagation (VEBP)." In VEBP, teaming is performed in two steps: (a) The velocity vector field of reference trajectories is approximated by a feedforward neural network (NN) with biconnection layers by backpropagating the velocity errors directly. (b) The RNN is constructed by adding integrators and output feedback loops to the trained feedforward NN. VEBP has some advantages over "backpropagation through time (BPTT)," the conventional learning method for RNNs. The effectiveness of the presented RNN and its learning algorithm is demonstrated by simulation results for some examples of nonlinear dynamics. (C) 2002 Wiley Periodicals, Inc.

关键词： recurrent neural network approximation learning algorithm dynamics backpropagation

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning of fuzzy logic controllers for quadruped walking robots 15th

Reinforcement learning of fuzzy logic controllers for quadru...

引用

15th World Congress of the International Federation of Automatic Control, 2002

作者： Gu, Dongbing Hu, Huosheng Department of Computer Science University of Essex Wivenhoe Park Colchester United Kingdom

This paper presents a fuzzy logic controller (FLC) for the implementation of some behaviour of Sony legged robots. The adaptive heuristic Critic (AHC) reinforcement learning is employed to refine the FLC. The actor part of AHC is a conventional FLC in which the parameters of input membership functions are learned by an immediate internal reinforcement signal. This internal reinforcement signal comes from a prediction of the evaluation value of a policy and the external reinforcement signal. The evaluation value of a policy is learned by temporal difference (TD) learning in the critic part that is also represented by a FLC. A genetic algorithm (GA) is employed for learning internal reinforcement of the actor part because it is more efficient in searching than other trial and error search approaches. Copyright © 2002 IFAC.

关键词： Fuzzy logic controller learning algorithm Robot control

来源：评论

学校读者我要写书评

暂无评论

Airborne sonar target recognition using artificial neural network

引用

MATHEMATICAL AND COMPUTER MODELLING 2002年第3-4期35卷 429-440页

作者： Liang, M Palakal, MJ Indiana Univ Purdue Univ Dept Comp & Informat Sci Indianapolis IN 46202 USA Lucent Technol Inc Holmdel NJ 07733 USA

Airborne sonar target recognition involves two key technical issues: target feature extraction and classification. In this paper, the issue designing a feature classifier with high classification accuracy is discussed. Generally, the multilayered feed-forward neural network can be applied to the airborne sonar target feature classification to achieve the high performance requirement. However, neural networks trained by conventional error back-propagation (B-P) learning algorithms suffer from slow convergence rate and inadequate generalization ability, Detailed analysis of the B-P algorithm reveals that these problems are mainly related to the magnitudes of the components of the gradient vector and the direction of the vector associated with the severely ill-conditioned nature of the Hessian matrix of the error function. A fast back-propagation (F-BP) algorithm is therefore developed to accelerate the learning speed of the B-P algorithm. A dynamic training strategy is then applied to the F-BP algorithm to improve the generalization ability. Experiments are carried out for airborne sonar target feature classification using these algorithms. The results show that the performance of the neural network classifier trained with the proposed algorithm is superior to that of traditional B-P algorithm with a seven-fold learning speed advantage over B-P. (C) 2002 Elsevier Science Ltd. All rights reserved.

关键词： target recognition neural network learning algorithm dynamic training fast learning algorithm generalization nonparameter classifier

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：