基于智能算法的神经网络优化及其应用
|
摘要
随着人工神经网络越来越广泛地被应用于各类科研领域,对其优化算法和应用技术的研究成了人工神经网络领域的重点方向。目前,在利用智能算法优化神经网络、应用神经网络实现模糊推理控制这2方面,已经取得了一定进展,但存在着训练数据成几何形增大,应用性能不稳定等缺陷。在充分研究神经网络、群体智能算法、模糊逻辑基本概念的基础上,本文利用新的群体智能算法优化神经网络结构和学习规则,实现有监督模糊聚类、自适应神经-模糊控制,做了以下工作:
1、提出了一种基于QPSO(Quantum Particle Swarm Optimization)的神经网络训练算法,并对神经网络进行训练,将其结果与传统神经网络训练算法相比较,该算法具有收敛速度快,对数据离散程度高的问题更易实现全局收敛的特点。
2、提出了基于群体智能集成的神经网络结构优化算法,采用间接编码方案表达网络结构,利用二维细胞自动机中的元细胞表示网络连接,对元细胞的坐标和值分别演化,实现网络结构的生长和剪枝,其中包括:利用二进制量子化粒子群算法BQPSO(Binary Quantum Particle Swarm Optimization),导出特定的适应度函数,生成并进化元细胞的坐标;利用元细胞邻域演化规则,演化元细胞的值;利用浮点量子化粒子群算法QPSO训练当前网络;最后得到最终稳定的网络结构及其参数。
本算法采用元细胞的坐标和值分别演化,突破了目前常见的网络结构设计算法中,结构编码方案的长度成几何形膨胀、且不易实现的局限性。
3、在研究有监督模糊聚类SFCM(Supervised Fuzzy C-Clustering)神经网络的基础上,提出了一种新的结合输入空间聚类特性和输出空间实时逼近特性的模糊聚类目标函数,在模糊聚类中引入监督因素,构造并实现一种新型的模糊聚类神经网络。
该方法在初值敏感性、有效收敛稳定性、收敛速度等方面相对于传统模糊聚类都有明显改善。
4、针对机器人在未知、复杂环境下从源到目标之间,自主避开各种类型的障碍的问题,设计了神经-模糊控制算法实现动态路径规划,包括:模糊控制体系,实现输入模糊化、模糊推理规则库、输出去模糊化控制;根据规则库设计实现模糊控制的神经网络,简化了网络结构和参数集;基于QPSO的网络训练;机器人状态变量的记忆、环境信息的设置和管理策略,解决了“U”型障碍物内的死循环路径问题。
本算法有效的解决了常规神经-模糊控制系统中,有可能造成机器人死循环路径的“U”型障碍物跨越问题,以及因网络规模大和采用传统的梯度下降训练法训练网络而带来的性能问题。
Along with wider application of artificial neural network, the optimization algorithm and the application technique of it have become the most important research orientation in the field. At present, certain progress has been made in the fields of neural network optimization using intelligent algorithm and fuzzy logic control using neural network, but there still exists the limitation of geometrically growing training data and the unstable performances. Based on sufficient research in the basic conceptions of neural network, colony intelligent algorithm and fuzzy logic, the optimization of the structure design and learning rule of neural network by using novel colony intelligent algorithm, the realization of supervised fuzzy clustering and adaptive neural-fuzzy control by using optimized neural network, have been discussed in the thesis.
1. A training algorithm of neural network based on QPSO is proposed, which train the neural network by means of the quantum particle swarm optimization. The algorithm show better convergent speed and better global convergent characteristic when dealing with more dispersed issue compared with the traditional neural network training algorithm.
2. A novel algorithm of neural network structure design based on BQPSO and 2-dimension cellular automate system is proposed. The algorithm introduces unique indirect encoding schema representing the structure of neural network, using the cell in the 2-dimension cellular automate system representing the existence of connection in neural network, by separately evolving the coordinates and value of the cell, the growing and pruning of the network structure is achieved. Create and evolve the coordinates of the cell by virtue of BQPSO with specially-designed fitness function, evolve the value of the cell using properly-designed neighboring evolving rule of cellular system, train current network with float-point QPSO, the final stable structure is found step by step.
By separately evolving the coordinates and value of the cell, the proposed algorithm can solve the problem of geometrically growing encoding length and the difficult realization of commonly used structure design algorithm.
3. The research of the supervised fuzzy C-clustering neural network. A novel objective function of fuzzy clustering that integrates the clustering characteristic of input space and the real-time approximate characteristic of output space is proposed, thus importing the supervise factor into the former fuzzy clustering. An extraordinary neural network handling the SFCM is also proposed.
SFCM has better performance in the stable convergent rate, convergent speed, as well as in the initial condition sensitivity compared with traditional fuzzy clustering.
4. The research of the neural-fuzzy control. According to the issue of dynamic path plan of mobile robot in unknown environments from the start to the destination with obstacle avoidance, a systemic neural-fuzzy control algorithm is proposed. Fuzzy logic control is designed to do the input fuzzification, fuzzy reasoning rule base, output defuzzification. The simplified structure of neural network handling the fuzzy control based on the rule base and the corresponding simplified network parameter set is also designed. Train the network using QPSO. Solve the "dead cycle" problem in U-shaped obstacle through the storage and management strategy of state variable of robot.
The algorithm solve the problem of big network scale, low network performance via using grade-descend training method in the conventional neural-fuzzy system, and the problem of getting into the dead cycle when striding across the U-shaped obstacle is also solved.
1、提出了一种基于QPSO(Quantum Particle Swarm Optimization)的神经网络训练算法,并对神经网络进行训练,将其结果与传统神经网络训练算法相比较,该算法具有收敛速度快,对数据离散程度高的问题更易实现全局收敛的特点。
2、提出了基于群体智能集成的神经网络结构优化算法,采用间接编码方案表达网络结构,利用二维细胞自动机中的元细胞表示网络连接,对元细胞的坐标和值分别演化,实现网络结构的生长和剪枝,其中包括:利用二进制量子化粒子群算法BQPSO(Binary Quantum Particle Swarm Optimization),导出特定的适应度函数,生成并进化元细胞的坐标;利用元细胞邻域演化规则,演化元细胞的值;利用浮点量子化粒子群算法QPSO训练当前网络;最后得到最终稳定的网络结构及其参数。
本算法采用元细胞的坐标和值分别演化,突破了目前常见的网络结构设计算法中,结构编码方案的长度成几何形膨胀、且不易实现的局限性。
3、在研究有监督模糊聚类SFCM(Supervised Fuzzy C-Clustering)神经网络的基础上,提出了一种新的结合输入空间聚类特性和输出空间实时逼近特性的模糊聚类目标函数,在模糊聚类中引入监督因素,构造并实现一种新型的模糊聚类神经网络。
该方法在初值敏感性、有效收敛稳定性、收敛速度等方面相对于传统模糊聚类都有明显改善。
4、针对机器人在未知、复杂环境下从源到目标之间,自主避开各种类型的障碍的问题,设计了神经-模糊控制算法实现动态路径规划,包括:模糊控制体系,实现输入模糊化、模糊推理规则库、输出去模糊化控制;根据规则库设计实现模糊控制的神经网络,简化了网络结构和参数集;基于QPSO的网络训练;机器人状态变量的记忆、环境信息的设置和管理策略,解决了“U”型障碍物内的死循环路径问题。
本算法有效的解决了常规神经-模糊控制系统中,有可能造成机器人死循环路径的“U”型障碍物跨越问题,以及因网络规模大和采用传统的梯度下降训练法训练网络而带来的性能问题。
Along with wider application of artificial neural network, the optimization algorithm and the application technique of it have become the most important research orientation in the field. At present, certain progress has been made in the fields of neural network optimization using intelligent algorithm and fuzzy logic control using neural network, but there still exists the limitation of geometrically growing training data and the unstable performances. Based on sufficient research in the basic conceptions of neural network, colony intelligent algorithm and fuzzy logic, the optimization of the structure design and learning rule of neural network by using novel colony intelligent algorithm, the realization of supervised fuzzy clustering and adaptive neural-fuzzy control by using optimized neural network, have been discussed in the thesis.
1. A training algorithm of neural network based on QPSO is proposed, which train the neural network by means of the quantum particle swarm optimization. The algorithm show better convergent speed and better global convergent characteristic when dealing with more dispersed issue compared with the traditional neural network training algorithm.
2. A novel algorithm of neural network structure design based on BQPSO and 2-dimension cellular automate system is proposed. The algorithm introduces unique indirect encoding schema representing the structure of neural network, using the cell in the 2-dimension cellular automate system representing the existence of connection in neural network, by separately evolving the coordinates and value of the cell, the growing and pruning of the network structure is achieved. Create and evolve the coordinates of the cell by virtue of BQPSO with specially-designed fitness function, evolve the value of the cell using properly-designed neighboring evolving rule of cellular system, train current network with float-point QPSO, the final stable structure is found step by step.
By separately evolving the coordinates and value of the cell, the proposed algorithm can solve the problem of geometrically growing encoding length and the difficult realization of commonly used structure design algorithm.
3. The research of the supervised fuzzy C-clustering neural network. A novel objective function of fuzzy clustering that integrates the clustering characteristic of input space and the real-time approximate characteristic of output space is proposed, thus importing the supervise factor into the former fuzzy clustering. An extraordinary neural network handling the SFCM is also proposed.
SFCM has better performance in the stable convergent rate, convergent speed, as well as in the initial condition sensitivity compared with traditional fuzzy clustering.
4. The research of the neural-fuzzy control. According to the issue of dynamic path plan of mobile robot in unknown environments from the start to the destination with obstacle avoidance, a systemic neural-fuzzy control algorithm is proposed. Fuzzy logic control is designed to do the input fuzzification, fuzzy reasoning rule base, output defuzzification. The simplified structure of neural network handling the fuzzy control based on the rule base and the corresponding simplified network parameter set is also designed. Train the network using QPSO. Solve the "dead cycle" problem in U-shaped obstacle through the storage and management strategy of state variable of robot.
The algorithm solve the problem of big network scale, low network performance via using grade-descend training method in the conventional neural-fuzzy system, and the problem of getting into the dead cycle when striding across the U-shaped obstacle is also solved.
引文
[1]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].西安:西安交通大学出版社,2002.2-3
[2]Simon Haykin.神经网络原理[M].叶世伟等译.北京:机械工业出版社,2004.1
[3]Sjmon Haykin.神经网络原理[M].叶世伟等译.北京:机械工业出版,2004.17-10
[4]Rosenblatt F.The perceptron:A Probabilistic Model for Mnformation Storage and Organization in the Brain[J].Psychological Review,1958,65:386-408
[5]Widrow B,M.E.Hoff.Adaptive Switching Circuits[C].IRE WESCON Convention Record:part 4,Computers:Man-Machine Systems,Los Angeles,1960,:96-104.
[6]Minsky M,S Papert.Perceptrons[M].MIT Press,Cambridge,MA,1969
[7]Hopfield J.Neurons with Graded Response have Collective Computational Properties Like those of Two-state Neurons[J].Proc.Natl.Acad.Sci.1984,81:3088-3092
[8]Rumelhart D.E.,Cs E.Hinton and R.J.Williams.Learning Representations by Back-Propagating Enors[J].Nature,1986,323(9):533-536
[9]Hecht-Nielsen R.Neurocomputing[[M].Addison-Wesley.Reading,MA,1990
[10]Holland J.H.Adaptation in Natural and Artificial Systems[M].The University of Michigan Press,1975
[11]Fogel L.J.,Owens A.J and Walsh,M.J.Artificial Intelligence through Simulated Evolution[M].John Wiley,New York.1966
[12]Koza J.R.Genetic Programming:On the Programming of Computers by Means of Natural Selection[M].MIT Press,Cambridge,1992
[13]Colonia Dorigom,Maniezzo,V.Distriuted Optimization by Ant Colonies[C].Proc.the first European Conference on Artificial Life.1991:134-142
[14]J.Kennedy,R.Eberhart.Particle Swarm Optimization[C].IEEE int.Conf.on Neural Network,1995,1942-1948
[15]Kennedy,J.Eberhart,R.C.a Discrete Binary Version of the Particle Swarm Algorithm[C].Proc.1997 Conf.on Systems,Man,and Cybernetics,4104-4109
[16]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].西安:西安交通大学出版社,2002.9-10
[17]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].西安:西安交通大学出版社,2002.42-44
[18]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].西安:西安交通大学出版社.2002.45-49
[19]Zadeh,L.A.Fuzzy Sets[J].Information and Control,1968,Vol.8,338-353
[20]D.L.Gray,A.N.Michel.a Training Algorithm for Binary Feed-Forward Neural Networks[J].IEEE Trans.Neural Networks,Mar.1993
[21]J.H.Kim,Sung-Kwon,Park.the Geometrical Learning of Binary Neural Networks[J].IEEE Trans.Neural Networks,1995,vol.6,no.1
[22]Miller.G..F,Todd.P,Hegde.S.Designing Neural Networks using Genetic Algorithm[C].Proceedings of the 3th International Conference on GAs.MorganKanfmann.1989.379-384
[23]John.W.L.Merril.Fractally Configured Neural Network[J].Neural Netwoks,1991.4.53-60
[24]Witold Pedrycz,George Vukovich.Logic-oriented Fuzzy Clustering[J].Pattern Recognition Letters 23,2002,1515-1527
[25]Dunn J.A Fuzzy Relative of ISO DATA Process and Its Use in Detecting Compact Well Separated Clusters[J].Journal of Cybernet,1974.3(3):32-57
[26]Bezdek J.C.Fuzzv Mathematics in Pattern Classifications[D].[PhD dissertation].Ithaca:Cornell Universitv,NY.1973
[27]Pal S.K,Mitra S.Multilayer Perceptron,Fuzzy Sets,and Classification[J].IEEE.Tranc on Neural Networks,lO92,3(5):683-697
[28]Kohonen T.Self-Organization and Associative Memory[M].Berlin,Germany:Springer-Verlag,1989
[29]Zhang D.D.Neural Network System Design Methodology[D].[PhD dissertation].Beijing:Tsinghua University,1996,17-20
[30]何丕廉,侯越先.模糊聚类神经网络的非对称学习[J].计算机应用与发 展,2001,38(3):296-301
[31]Y.Shi,R.Eberhart.Parameter Selection in Particle Swarm Optimization[C].Seventh annual Conf.On Evolutionary Programming,March 1998,591-601
[32]M.Clerc,J.Kennedy.the Particle:Explosion,stability and convergence in a Muilti-Dimensional Complex Space[J].IEEE int.Transaction on Evolutionary Programming,2002.6(1).58-73
[33]Y.Shi,R.Eberhart.Empirical study of particle swarm optimization[C].Washington:Proc.of Congress on Evolutionary Computation,1999.1945-1950
[34]R.Eberhart,Y.Shi.Particle Swarm Optimization developments applications and resources[C].Piscataway:IEEE int.Conf.On Evolutionary Computation,2001.81-86
[35]S.Becker,G.E.Hinton.A self-organizing Neural Network that Discovers Surfaces in Random-dot Stereograms[J].Nature,2001.355.161-163
[36]M.Clerc.The Swarm and Queen:Towards a Deterministic and Adaptive Particle Swarm Optimization[C].Piscataway:Proc.Congress on Evolutionary Computation,1999.1951-1957
[37]J.Sun,B.Feng Wenbo Xu.Particle Swarm Optimization with Particles Having Quantum Behavior[C].IEEE int.Conf.on evolutionary computation,2004,325-331
[38]J.Sun,W.B.Xu et al.a Global Search Strategy of Quantum-Behaved Particle Swarm Optimization[C].IEEE int.Conf.on Cybernetics and Intelligent System,2004,111-116
[39]陈伟,冯斌,孙俊.基于QPSO的RBF 神经网络参数优化仿真研究.计算机应用,2006.26(8).1928-1931
[40]Hecht-Nielsen.R.Kolmogorov's Mapping Neural Network Existence Theorem[C].First International Conference on Neural Networks,vol.Ⅲ,11-14
[41]王薇,吴敏,陈晓方,桂卫华.基于多种群并行遗传算法的原料库存优化[J].控制工程,2003,10(1).33-36
[42]S.Becker,G.E.Hinton.A self-organizing Neural Network that Discovers Surfaces in Random-dot Stereograms[J].Nature,vol.355,161-163
[43]Reed R.Pruning Algorithms A Survey[J].IEEE.Trans.NN,1993,4:740-747
[44]Von Newmann.Theory of Self-Reproduction Automata(edited and completed by A.W.Burks)[M].Urbana,IL:University of Ilinois Press,1966
[45]S.Wolfram.Universitv and Complexity in Cellular Automata[J].Physica D,1984,10(1):1-35
[46]张传武.细胞自动机及其理论研究进展[J].贵州大学报,2004.21(3),289-292
[47]遭兴芹,王能超.新型细胞自动机规则空间的参数化[J].计算机科学.2007,34(3),145-148
[48]Jun Sun,Wenbo Xu,Wei Fang,ZhiLei Cai.Quantum-Behaved Particle Swarm Optimization with Binary Encoding[C].Proc.The 8th International Conference on Adaptive and Natural Computing Algorithms.2007,376-385
[49]Fang Bao,Yonghui Pan,Wenbo Xu.A Novel Training Algorithm for BP neural Network[C].Proceedings of the International Symposium on distributed Computing and Application to Business,Engineering and Science 2006.767-770
[50]Soniag E.D.Feedforward Nets for Interpolation and Classification[J].Journal of Computer and System Science,2003,Vol 45
[51]韩庆兰,梅运先.基于BP人工神经网络的物流配送中心选址决策[J].中因软科学.2004.6.140-143
[52]Ruspini E H.a New Approach to Clustering[J].Inf Cont,1969,15:22-32
[53]Jim C.Bezdek.Pattern Recognition with Fuzzy Objective Function Algorithm[M].New York:Plenum Press,1981
[54]Pezdrcy P.Algorithms of Fuzzy Clustering with Partial Supervision[J].Pattern Recognition.Letters,1985,3:13-20
[55]David Zhang,Sankar K.Pal.A Fuzzy Clustering Neural Network(FCNs) System Design Methodology.IEEE Transaction on Neural Network.2000,vol.11(5),pp.1174-1177
[56]Witold Pedrycz,George Vukovich.Logic-oriented Fuzzy Clustering.Pattern Recognition Letters.2002,vol.23,pp.1515-1527
[57]J.Abonyi,F.Szeifert.Supervised Fuzzy for the Identification of Fuzzy Classifiers[J].Pattern Recoginition Letters.2003.24(14).2195-220
[58]A.Bensaid,L.O.Hall,J.C.Bezdek,L.P.Clarke.Partially Supervised Clustering for Image Segmentation[J].Pattern Recognition.1996.29(5).859-871
[59]A.Staiano,R.Tagliaferri,W.Pedrycz.Improving RBF networks performance in regression tasks by means of a supervised fuzzy clustering[J].Neurocomputing,2006.69.1570-1581
[60]邓赵红,王士同.鲁棒性的模糊聚类神经网络[J].软件学报,2005.16(8).1415-1422
[61]Xiaoou Tang,Xinbo Gao and Jianzhuang Liu.A Spatial-Temporal Approach for Video Caption Detection and Recognition[J].IEEE Transaction on Neural Network.2002,13(4).961-971
[62]Jain A K,Moreau J V.Bootstrap techniques in cluster analysis[J].Pattern Recognition,1997,20(5):547-563
[63]Ban Kosko.模糊工程[M].黄崇福译.西安:西安交通大学出版社,1996.118-126,60-72
[64]王士同.模糊系统模糊神经网络及应用程序设计[M].上海:上海科技文献出版社,2000.82-88
[65]Yupu Yang,Xiaoming Xu,Wenyuan Zhang.Design neural network based fuzzy logic[J].Fuzzy Sets and System.2000,114:325
[66]丁承君,张明路,段萍.模糊神经网络在移动机器人信息融合中的应用[J].控制理论与应用,2004,21(1):59
[67]Amari,S.F.Learning Patterns and Pattern Sequences by Self-organizing Nets of Threshold Elements[J].IEEE Transactions on Computers,1992,C21:1197-1206
[68]Sugeno M.,Takahiro Y.A Fuzzy-logic-based Approach to Qualitative Modeling[J].IEEE Transactions on Fuzzy Systems.1993.1(1).7-31
[69]Bruse J.Veloso M.Real-time Randomized Path Planning for Robot Navigation[C].Proceedings for the IEEE/RSJ International Conference on Intelligent Robots and System,2002,3:2383-2388
[70]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].西安:西安交通大学出版社,2002.52-54
[2]Simon Haykin.神经网络原理[M].叶世伟等译.北京:机械工业出版社,2004.1
[3]Sjmon Haykin.神经网络原理[M].叶世伟等译.北京:机械工业出版,2004.17-10
[4]Rosenblatt F.The perceptron:A Probabilistic Model for Mnformation Storage and Organization in the Brain[J].Psychological Review,1958,65:386-408
[5]Widrow B,M.E.Hoff.Adaptive Switching Circuits[C].IRE WESCON Convention Record:part 4,Computers:Man-Machine Systems,Los Angeles,1960,:96-104.
[6]Minsky M,S Papert.Perceptrons[M].MIT Press,Cambridge,MA,1969
[7]Hopfield J.Neurons with Graded Response have Collective Computational Properties Like those of Two-state Neurons[J].Proc.Natl.Acad.Sci.1984,81:3088-3092
[8]Rumelhart D.E.,Cs E.Hinton and R.J.Williams.Learning Representations by Back-Propagating Enors[J].Nature,1986,323(9):533-536
[9]Hecht-Nielsen R.Neurocomputing[[M].Addison-Wesley.Reading,MA,1990
[10]Holland J.H.Adaptation in Natural and Artificial Systems[M].The University of Michigan Press,1975
[11]Fogel L.J.,Owens A.J and Walsh,M.J.Artificial Intelligence through Simulated Evolution[M].John Wiley,New York.1966
[12]Koza J.R.Genetic Programming:On the Programming of Computers by Means of Natural Selection[M].MIT Press,Cambridge,1992
[13]Colonia Dorigom,Maniezzo,V.Distriuted Optimization by Ant Colonies[C].Proc.the first European Conference on Artificial Life.1991:134-142
[14]J.Kennedy,R.Eberhart.Particle Swarm Optimization[C].IEEE int.Conf.on Neural Network,1995,1942-1948
[15]Kennedy,J.Eberhart,R.C.a Discrete Binary Version of the Particle Swarm Algorithm[C].Proc.1997 Conf.on Systems,Man,and Cybernetics,4104-4109
[16]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].西安:西安交通大学出版社,2002.9-10
[17]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].西安:西安交通大学出版社,2002.42-44
[18]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].西安:西安交通大学出版社.2002.45-49
[19]Zadeh,L.A.Fuzzy Sets[J].Information and Control,1968,Vol.8,338-353
[20]D.L.Gray,A.N.Michel.a Training Algorithm for Binary Feed-Forward Neural Networks[J].IEEE Trans.Neural Networks,Mar.1993
[21]J.H.Kim,Sung-Kwon,Park.the Geometrical Learning of Binary Neural Networks[J].IEEE Trans.Neural Networks,1995,vol.6,no.1
[22]Miller.G..F,Todd.P,Hegde.S.Designing Neural Networks using Genetic Algorithm[C].Proceedings of the 3th International Conference on GAs.MorganKanfmann.1989.379-384
[23]John.W.L.Merril.Fractally Configured Neural Network[J].Neural Netwoks,1991.4.53-60
[24]Witold Pedrycz,George Vukovich.Logic-oriented Fuzzy Clustering[J].Pattern Recognition Letters 23,2002,1515-1527
[25]Dunn J.A Fuzzy Relative of ISO DATA Process and Its Use in Detecting Compact Well Separated Clusters[J].Journal of Cybernet,1974.3(3):32-57
[26]Bezdek J.C.Fuzzv Mathematics in Pattern Classifications[D].[PhD dissertation].Ithaca:Cornell Universitv,NY.1973
[27]Pal S.K,Mitra S.Multilayer Perceptron,Fuzzy Sets,and Classification[J].IEEE.Tranc on Neural Networks,lO92,3(5):683-697
[28]Kohonen T.Self-Organization and Associative Memory[M].Berlin,Germany:Springer-Verlag,1989
[29]Zhang D.D.Neural Network System Design Methodology[D].[PhD dissertation].Beijing:Tsinghua University,1996,17-20
[30]何丕廉,侯越先.模糊聚类神经网络的非对称学习[J].计算机应用与发 展,2001,38(3):296-301
[31]Y.Shi,R.Eberhart.Parameter Selection in Particle Swarm Optimization[C].Seventh annual Conf.On Evolutionary Programming,March 1998,591-601
[32]M.Clerc,J.Kennedy.the Particle:Explosion,stability and convergence in a Muilti-Dimensional Complex Space[J].IEEE int.Transaction on Evolutionary Programming,2002.6(1).58-73
[33]Y.Shi,R.Eberhart.Empirical study of particle swarm optimization[C].Washington:Proc.of Congress on Evolutionary Computation,1999.1945-1950
[34]R.Eberhart,Y.Shi.Particle Swarm Optimization developments applications and resources[C].Piscataway:IEEE int.Conf.On Evolutionary Computation,2001.81-86
[35]S.Becker,G.E.Hinton.A self-organizing Neural Network that Discovers Surfaces in Random-dot Stereograms[J].Nature,2001.355.161-163
[36]M.Clerc.The Swarm and Queen:Towards a Deterministic and Adaptive Particle Swarm Optimization[C].Piscataway:Proc.Congress on Evolutionary Computation,1999.1951-1957
[37]J.Sun,B.Feng Wenbo Xu.Particle Swarm Optimization with Particles Having Quantum Behavior[C].IEEE int.Conf.on evolutionary computation,2004,325-331
[38]J.Sun,W.B.Xu et al.a Global Search Strategy of Quantum-Behaved Particle Swarm Optimization[C].IEEE int.Conf.on Cybernetics and Intelligent System,2004,111-116
[39]陈伟,冯斌,孙俊.基于QPSO的RBF 神经网络参数优化仿真研究.计算机应用,2006.26(8).1928-1931
[40]Hecht-Nielsen.R.Kolmogorov's Mapping Neural Network Existence Theorem[C].First International Conference on Neural Networks,vol.Ⅲ,11-14
[41]王薇,吴敏,陈晓方,桂卫华.基于多种群并行遗传算法的原料库存优化[J].控制工程,2003,10(1).33-36
[42]S.Becker,G.E.Hinton.A self-organizing Neural Network that Discovers Surfaces in Random-dot Stereograms[J].Nature,vol.355,161-163
[43]Reed R.Pruning Algorithms A Survey[J].IEEE.Trans.NN,1993,4:740-747
[44]Von Newmann.Theory of Self-Reproduction Automata(edited and completed by A.W.Burks)[M].Urbana,IL:University of Ilinois Press,1966
[45]S.Wolfram.Universitv and Complexity in Cellular Automata[J].Physica D,1984,10(1):1-35
[46]张传武.细胞自动机及其理论研究进展[J].贵州大学报,2004.21(3),289-292
[47]遭兴芹,王能超.新型细胞自动机规则空间的参数化[J].计算机科学.2007,34(3),145-148
[48]Jun Sun,Wenbo Xu,Wei Fang,ZhiLei Cai.Quantum-Behaved Particle Swarm Optimization with Binary Encoding[C].Proc.The 8th International Conference on Adaptive and Natural Computing Algorithms.2007,376-385
[49]Fang Bao,Yonghui Pan,Wenbo Xu.A Novel Training Algorithm for BP neural Network[C].Proceedings of the International Symposium on distributed Computing and Application to Business,Engineering and Science 2006.767-770
[50]Soniag E.D.Feedforward Nets for Interpolation and Classification[J].Journal of Computer and System Science,2003,Vol 45
[51]韩庆兰,梅运先.基于BP人工神经网络的物流配送中心选址决策[J].中因软科学.2004.6.140-143
[52]Ruspini E H.a New Approach to Clustering[J].Inf Cont,1969,15:22-32
[53]Jim C.Bezdek.Pattern Recognition with Fuzzy Objective Function Algorithm[M].New York:Plenum Press,1981
[54]Pezdrcy P.Algorithms of Fuzzy Clustering with Partial Supervision[J].Pattern Recognition.Letters,1985,3:13-20
[55]David Zhang,Sankar K.Pal.A Fuzzy Clustering Neural Network(FCNs) System Design Methodology.IEEE Transaction on Neural Network.2000,vol.11(5),pp.1174-1177
[56]Witold Pedrycz,George Vukovich.Logic-oriented Fuzzy Clustering.Pattern Recognition Letters.2002,vol.23,pp.1515-1527
[57]J.Abonyi,F.Szeifert.Supervised Fuzzy for the Identification of Fuzzy Classifiers[J].Pattern Recoginition Letters.2003.24(14).2195-220
[58]A.Bensaid,L.O.Hall,J.C.Bezdek,L.P.Clarke.Partially Supervised Clustering for Image Segmentation[J].Pattern Recognition.1996.29(5).859-871
[59]A.Staiano,R.Tagliaferri,W.Pedrycz.Improving RBF networks performance in regression tasks by means of a supervised fuzzy clustering[J].Neurocomputing,2006.69.1570-1581
[60]邓赵红,王士同.鲁棒性的模糊聚类神经网络[J].软件学报,2005.16(8).1415-1422
[61]Xiaoou Tang,Xinbo Gao and Jianzhuang Liu.A Spatial-Temporal Approach for Video Caption Detection and Recognition[J].IEEE Transaction on Neural Network.2002,13(4).961-971
[62]Jain A K,Moreau J V.Bootstrap techniques in cluster analysis[J].Pattern Recognition,1997,20(5):547-563
[63]Ban Kosko.模糊工程[M].黄崇福译.西安:西安交通大学出版社,1996.118-126,60-72
[64]王士同.模糊系统模糊神经网络及应用程序设计[M].上海:上海科技文献出版社,2000.82-88
[65]Yupu Yang,Xiaoming Xu,Wenyuan Zhang.Design neural network based fuzzy logic[J].Fuzzy Sets and System.2000,114:325
[66]丁承君,张明路,段萍.模糊神经网络在移动机器人信息融合中的应用[J].控制理论与应用,2004,21(1):59
[67]Amari,S.F.Learning Patterns and Pattern Sequences by Self-organizing Nets of Threshold Elements[J].IEEE Transactions on Computers,1992,C21:1197-1206
[68]Sugeno M.,Takahiro Y.A Fuzzy-logic-based Approach to Qualitative Modeling[J].IEEE Transactions on Fuzzy Systems.1993.1(1).7-31
[69]Bruse J.Veloso M.Real-time Randomized Path Planning for Robot Navigation[C].Proceedings for the IEEE/RSJ International Conference on Intelligent Robots and System,2002,3:2383-2388
[70]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].西安:西安交通大学出版社,2002.52-54