计算智能问题研究
|
摘要
从生命现象和人类的智能活动中得到启发,人们提出了计算智能方法来解决许多复杂问题,形成了以人工神经网络、进化计算与模糊逻辑为代表的三个典型分支。本文主要针对计算智能中的人工神经网络与进化计算这两个领域展开一些理论及应用问题研究。论文主要工作和创新点包括:
1.研究了现代神经网络-神经场的特征、理论和方法。
2.通过构造Lyapunov-Krasovskii函数和线性矩阵不等式(LMI),给出了判定时滞反应-扩散不确定神经网络的全局指数鲁棒稳定性的一种新的实用的LMI方法。
3.研究了遗传算法的混合改进策略,提出了一种新的混合遗传算法:采用混沌序列产生初始种群、多个交叉后代竞争择优和自适应变异来改进遗传操作;并通过精英个体保留、二次插值和改进遗传操作三种策略共同产生种群新个体,以克服标准遗传算法的收敛速度慢、早熟等缺陷。
4.为解决神经网络的过度学习问题,提出一种综合适应度作为训练指标,以混合遗传算法为学习算法训练神经网络,有利于避免神经网络对训练样本集的过度学习,改善了神经网络的泛化能力。
5.研究了粒子群算法的种群多样性测度,提出了一种新的基于种群多样性的自适应粒子群算法:通过对种群多样性测度新指标的应用,自适应粒子群算法采用精英保留变异操作、新的速度项和动态自适应惯性权重技术,防止了种群多样性的过早丧失,有效地平衡了粒子群寻优过程中的探索和开发。
6.使用动态罚函数法和标记罚函数法处理约束条件,将改进的粒子群算法应用于约束优化问题求解。
Learning from life phenomenon and the human being’s intelligence activity, People create computational intelligence methods to solve some complicated problems. There are three typical embranchments in the study of computational intelligence, such as artificial neural networks, evolutionary computation and fuzzy logic. This paper gives a comprehensive study on some theory and practice problems in the fields of artificial neural networks, evolutionary computation. The main contents are as following:
1. The feature, theory, and methods of the modern artificial neural networks–neural fields theory is introduced and summarized.
2. An easy-to-test criteria for global exponential robust stability of a class of reaction-diffusion uncertain neural networks with time-varying is established by the means of creating new Lyapunov-Krasovskii functional and linear matrix inequality (LMI).
3. A new hybrid genetic algorithm is proposed. It applies the strategies such as chaos series to produce initial population, multi-offspring competition, and adaptive mutation to improve the genetic operation. The hybrid algorithm can generate new individuals by the methods such as the elite reservation, quadratic interpolation and improved genetic operator, so that it can overcome the shortage of premature and slow convergence speed of the standard genetic algorithm.
4. A synthesize fitness function is proposed in the process of the training of artificial neural networks by using hybrid genetic algorithm in order to improve its learning ability.
5. A new adaptive particle swarm optimization algorithm which based on the measurements of population diversity is presented. Two measurements are proposed to indicate the swarm population diversity. The algorithm applies a special mutation operator to increase the swarm population diversity. New velocity term and dynamic inertia weight are also provided in the adaptive particle swarm optimization algorithm to balance the exploration and exploitation of the global optimization.
6. An improved particle swarm optimizer is applied in some constrained optimization problems by using the dynamic punishment functions method and the tag punishment functions methods to deal with the complicated constrain conditions.
1.研究了现代神经网络-神经场的特征、理论和方法。
2.通过构造Lyapunov-Krasovskii函数和线性矩阵不等式(LMI),给出了判定时滞反应-扩散不确定神经网络的全局指数鲁棒稳定性的一种新的实用的LMI方法。
3.研究了遗传算法的混合改进策略,提出了一种新的混合遗传算法:采用混沌序列产生初始种群、多个交叉后代竞争择优和自适应变异来改进遗传操作;并通过精英个体保留、二次插值和改进遗传操作三种策略共同产生种群新个体,以克服标准遗传算法的收敛速度慢、早熟等缺陷。
4.为解决神经网络的过度学习问题,提出一种综合适应度作为训练指标,以混合遗传算法为学习算法训练神经网络,有利于避免神经网络对训练样本集的过度学习,改善了神经网络的泛化能力。
5.研究了粒子群算法的种群多样性测度,提出了一种新的基于种群多样性的自适应粒子群算法:通过对种群多样性测度新指标的应用,自适应粒子群算法采用精英保留变异操作、新的速度项和动态自适应惯性权重技术,防止了种群多样性的过早丧失,有效地平衡了粒子群寻优过程中的探索和开发。
6.使用动态罚函数法和标记罚函数法处理约束条件,将改进的粒子群算法应用于约束优化问题求解。
Learning from life phenomenon and the human being’s intelligence activity, People create computational intelligence methods to solve some complicated problems. There are three typical embranchments in the study of computational intelligence, such as artificial neural networks, evolutionary computation and fuzzy logic. This paper gives a comprehensive study on some theory and practice problems in the fields of artificial neural networks, evolutionary computation. The main contents are as following:
1. The feature, theory, and methods of the modern artificial neural networks–neural fields theory is introduced and summarized.
2. An easy-to-test criteria for global exponential robust stability of a class of reaction-diffusion uncertain neural networks with time-varying is established by the means of creating new Lyapunov-Krasovskii functional and linear matrix inequality (LMI).
3. A new hybrid genetic algorithm is proposed. It applies the strategies such as chaos series to produce initial population, multi-offspring competition, and adaptive mutation to improve the genetic operation. The hybrid algorithm can generate new individuals by the methods such as the elite reservation, quadratic interpolation and improved genetic operator, so that it can overcome the shortage of premature and slow convergence speed of the standard genetic algorithm.
4. A synthesize fitness function is proposed in the process of the training of artificial neural networks by using hybrid genetic algorithm in order to improve its learning ability.
5. A new adaptive particle swarm optimization algorithm which based on the measurements of population diversity is presented. Two measurements are proposed to indicate the swarm population diversity. The algorithm applies a special mutation operator to increase the swarm population diversity. New velocity term and dynamic inertia weight are also provided in the adaptive particle swarm optimization algorithm to balance the exploration and exploitation of the global optimization.
6. An improved particle swarm optimizer is applied in some constrained optimization problems by using the dynamic punishment functions method and the tag punishment functions methods to deal with the complicated constrain conditions.
引文
[1]周春光,梁艳春,计算智能,长春:吉林大学出版社,2001.
[2]丁永生,计算智能——理论、技术与应用,北京:科学出版社,2004.
[3]刑文训,谢金星,现代优化计算方法,北京:清华大学出版社,2005.
[4]王凌,智能优化算法及其应用,北京:清华大学出版社,施普林格出版社,2001.
[5]阎平凡,张长水,人工神经网络与模拟进化计算,北京:清华大学出版社,2000.
[6] Hebb D O.The Organization of Behavior.New York:Wiley,1949.
[7] Eccles J C. Cholinergic and Inhibitory Synapses in A Pathway from Motor-axon Collaterals to Motorneurones. Journal physiology,1954,12(6):524.
[8] Rosenblatt F. The Perception: A Probablistic Model for Information storage and Organization in the Brain. Psychological Review,1958,23(68):386-408.
[9] Windrow B,Hoff M E,Adaptive Switching Ciruits.1960 IRE WESCON convention record:part 4. Computers:Man-Machine Systems,Losangles:96-104.
[10]Grossberg S,On the Serial Learning of Lists.Bio-science,1969,17(4):201-253.
[11]Grossberg S,Some Networks that Can Learn,Remember and Reproduce any Number of Compialted Space-time Patterns,II,stud Applied Mathematics 1970,4(49):135-166.
[12]Willshaw D J,Buneman O P,Longuest-higgins.HC Nature,1969,22(2):960.
[13]Nilsson,J,Learning chines:Foundations of Trainable Pattern Classifying, systems.McGraw-hill,New York,1965.
[14]Stein R B,Leung K V,Mangeron D,Oguztoreli M N,Improved Neuraonal models for Studying Neural Networks Kybernetik,1974,19(15):1-9.
[15]Heiden U.Ander,Existence of Periodic Solutions of a Nerve Equation.Biology Cybernitics,1976,23(21):37-39.
[16]Hopfield J J.Neural Networks and physical systems with emergent collective computational abilities.Proc Nat Acad Sci,1982,79:2554-2558.
[17]Marr D,Vision[M].San Francisco:WHF Freeman,1982.
[18]Kirkpatrick S,Gellat K C D,Veechi M P,Optimization by Simulated Annealing,Science,1983,220(4598):671-681
[19]Hinton G E,Sejuowshi T J,Ackley D H,Boltzmann Machines:Cotraint Satisfaction Networks that Learn.Carnegiemellon University,Tech,Report CMU-CS-84-119.1984.
[20]Piggio T,Analog model of Computation for III-posed Problems of Early Vision.Artificial Intelligence Lab Memo,783,MIT,1984.
[21]Poggio,T.Comtational Visionand Regularization Theory. Nature (Lond), 1985, 27(3):314-319
[22]Chua L O,Yand L.Celluar Neural networks:Theory.IEEE Transaction on Circuits and Systems,1988,35(10):1257-1272.
[23]Chua L O,Yand L,Celluar Neural Networks:Application,IEEE Transaction on Circuits and Systems,1988,35(10):1273-1290.
[24]Kosko,B.Adaptive Bidirectional Associative Memories.Applied Optical, 1987, 26(23):4647-4680.
[25]Kosko B,Bidirectional Associative Memories.IEEE Transaction On Man,System andCybernitics.1988,18(1):49-59.
[26]廖晓昕,细胞神经网络的数学理论(I)(II)。中国科学( A辑),1994, 24 (9):902-910:1037-1046.
[27]Qinghua Zhang and Albert Benveniste,Wavelet Networks,IEEE Transaction on Neural Networks,1992,3(6).889-898.
[28]P.S.Sastry,G.Santharam and K.P.Unnikrishnan,Memory Neuron Networks for Identification and Control of Dynamical systems.IEEE Transaction on Neural Networks,1994,5(2):306-319107
[29]Jenkins B K,A R Tanguay Jr,Optical Architectures for Neural Network Implementation,Handbook of Neural Computing and Neural Networks.MIT Press, Boston,1995:673-677.
[30]McAulay A D,Wand J,Ma C,Optical Heteroassciative Memory Using Spatial Light Rebroadcasters.Applied Optical,1990,29(14):2067-2073.
[31]Narendra K,Parthasarathy K,Identification and Control of Dynamical System Using Neural Networks.IEEE Transaction On Neural Networks,March 1990,1(1):4-27.
[32]Miller W T,Real time Application of Neural Networks for Sensor based Control of Robots.With Vision.IEEE Transaction On Man,System and Cybernitics 1989,23(19):825-831.
[33]Bulsari A,Some Analytical Solutions to the General Approximation Problem for Feedforword Neural Networks.Neural Networks,1993,(6):991-996.
[34]Aibara K, Chaotic Neural Networks.Physical Letter A, 1990,144(6,7):334-3340.
[35]Inoue M, Nagayoshi A., A Chaos Neuro-computer.Physical Letter A, 1991,158 (8):373-376.
[36]Inoue M,Nakamoto K.,Epilepsyina Chaos Neuro-computer Model.SPIEVOL,236,Chaos in Biology and Medicine,1993,77-84.
[37]Jokinen Petri A.On the relations between radial basis function networks and fuzzy system.In:Proceeding of INCNN’29,Vol.1, New York: IEEE, 1992, 1220-1225.
[38]Okada Hiroyuki,Initializing multilayer neural networks with fuzzy logic.In:Proceeding of INCNN’92,Vol.1, 1239-1244.42.
[39]Cai Yaling, Hon Keung Kwan,A fuzzy neural networks with fuzzy classification. In: Proceedings of ASMESCI’94, Wuhan: Process of Huazhong University of Science and Technology,1994:894~899.
[40]B E.Using spectral techniques for improved performance in ANN, Proc IEEE, 1993. 500-505.
[41]沈艳军,多输出神经元模型的多层前向神经,博士学位论文,华中科技大学,武汉,2004年10月.
[42]Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edition. Prentice Hall PTR,1998.
[43]Amari, S.,Nurata, N.: Information geometry. New York: AMS and Oxford University Press,2000.
[44]Amari, S.: Differential geometrical methods in statistics. Springer Lecture Notes in Statistics, New York; Springer-Verlag. 28(1985).
[45]Amari, S.: Differential geometry of a parametric family of invertible linear systems-Riemannian metric, dual affine connections and divergence.Mathematical Systems Theory. 20 (1987) 53-82.
[46]Amari, S.: Information geometry of EM and em algorithm for neural networks. Neural Networks. 8(9) (1995) 1379-1408.
[47]Amari, S., Kurata, K., Nagaoka, H.: Information geometry of Boltzmann machine. IEEE Trans. On Neural Networks. 3(2) (1992) 260-271.
[48]Amari,S.: Dualistic geometry of the manifold of higher-order neurons . Neural Networks. 4(4) (1991) 433-451.
[49]Amari, S., Murata, N.: Statistical theory of learning curves under entropic loss criterion. Neural Computation. 5(1992) 140-153.
[50]时小虎,Elman神经网络与进化算法的若干理论研究及应用,吉林大学博士学位论文,2006年6月。
[51]Hagan,M.T,Demuth H.B.and Beale M.Neural Network Design.Thomson Learning, USA, 1996.
[52]Widrow B,et al.Neural Networks Application in Industry.Business and Science. Communication of the ACM,1994,37:93-105.
[53]Fu L.M.An expert network for DNA sequence analysis.IEEE Intelligent Systems&Their Applications,1999,14(1):65-71.
[54]Campos M.and Lopez D.,Neural network approach to locate motifs in biosequences.Progress in Pattern Recognition,Image Analysis and Applications, Proceedings 3773,214-221(2005).
[55]Armano G.,Mancosu G.,Milanesi L.,Orro A.,Saba M.and Vargiu E.,A hybrid genetic-neural system for predicting protein secondary structure.Bmc Bioinformatics 6,(2005).
[56]Kato R.,Nakano H.,Konishi H.,Kato K.,Koga Y.,Yamane T.,Kobayashi T.and Honda H.,Novel strategy for protein exploration:High-throughput screening. assisted with fuzzy neural network.Journal of Molecular Biology 351,683-692 (2005)
[57]Coban R.and Can B.,Identification and control of ITU Triga Mark-II Nuclear Research Reactor using neural networks and fuzzy logic.Ai 2005:Advances in Artificial Intelligence 3809,1057-1062(2005).
[58]Pai P.F.and.Lin K.P,Application of hybrid learning neural fuzzy systems in reliability prediction.Quality and Reliability Engineering International 22, 199-211(2006).
[59]Guo H.J.,Lin S.F.and Liu J.H.,A radial basis function sliding mode controller for chaotic Lorenz system.Physics Letters A 351,257-261(2006).
[60]Liu Y.G.and Li Y.M.,Sliding mode adaptive neural-network control for nonholonomic mobile modular manipulators.Journal of Intelligent&Robotic Systems 44,203-224(2005).
[61]Sadjadian H.and Taghirad H.D.,Comparison of different methods for computing the forward kinematics of a redundant parallel manipulator.Journal of Intelligent&Robotic Systems 44,225-246(2005).
[62]Yildirim S.,Design of adaptive robot control system using recurrent neural network.Journal of Intelligent&Robotic Systems 44,247-261(2005).
[63]Li Y.,Liu G.,Hong T.and Liu K.,Robust control of a two-link flexible manipulator with quasi-static deflection compensation using neural networks.Journal ofIntelligent&Robotic Systems 44,263-276(2005).
[64]Tudoroiu,Patel R.and Khorasani K.,Neural network based control strategies fo N.r improving plasma characteristics in reactive ion etching. Neurocomputing 69,786-802(2006).
[65]Kim K.J.,Artificial neural networks with evolutionary instance selection for financial forecasting.Expert Systems with Applications,2006,30(3):519-526.
[66]Enke D.and Thawornwong S.,The use of data mining and neural networks for forecasting stock market returns.Expert Systems with Applications,2005,29(4): 927-940.
[67]Cao Q.,Leggio K.B.and Schniederians M.J.,A comparison between Fama and French's model and artificial neural networks in predicting the Chinese stock market.Computers&Operations Research, 2005,32(10):2499-2512.
[68]Huang W., Nakamori Y.and Wang S.Y.,Forecasting stock market movement direction with support vector machine. Computers & Operations Research, 2005,32(10):2513-2522.
[69]Armano G., Marchesi M.and Murru A.,A hybrid genetic-neural architecture for stock indexes forecasting.Information Sciences,2005,170(1):3-33.
[70]Kung S.Y.,et al.Neural Networks for Intelligent Multimedia Processing.Proc IEEE,1998, 86:1244-1272.
[71]Lang, S.: Differentail and Riemannian Manifolds. Springer-Veriag, New York. (1996).
[72]Hopfield,J.,Neural networks and physical system with emergent collective computational abilities. Proc. Nat. Acad. Sci., USA. 79 (1982) 2554-2558.
[73]Wang, L., Xu, D.: Global asymptotic stability of bidirectional associative memory neural networks with Stype distributed delays. International Journal of Systems Science. 33(11) (2002) 867-877.
[74]Wang, L., Xu, D.: global exponential stability of Hopfield reaction-diffusion neural networks with time-varying delays. Science in China (Series F). 46(6) (2003) 466-474.
[75]Wang LS, Gao YY, Global exponential robust stability of reaction-diffusion interval neural networks with time-varying delays, Physics Letters A, 2006; 350:342-348.
[76]Wang LS, Xu DY, Global exponential stability of Hopfield reaction-diffusion neural networks with time-varying delays, Science in China (Series F), 2003; 46(6):466-474.
[77]Liao XX, Fu YL, Gao J, Zhao ZQ, Stability of Hopfield neural networks with reaction -diffusion terms, Acta Electronica Sinica, 2000; 28:78-80.
[78]Edward R.D, Approximation of neural network dynamics by reaction-diffusion, Methods in the Applied Siences, 1998; 19(6):651-677.
[79]Luo X.Y, Cui B.T, Boundedness and exponential stability for nonautonomous cellular neural networks with reaction-diffusion terms, Chaos,Solitons and Fractals, 2007; 33:635-662.
[80]Song Q.K, Cao, J.D, Global exponential stability and existence of periodic solutions in BAM network with delays and reaction-diffusion terms,Chaos,Solitons and Fractals,2005,23:421-430.
[81]Cui B.T,Luo X.Y, Global exponential stability of BAM neural networks with distributed delays and reaction-diffusion terms, Chaos, Solitons and Fractals , 2006; 27:1347-1354.
[82]Zhou Q.G,Wan L,Sun J. H,Exponential stability of reaction-diffusion generalized Cohen-Grossberg neural networks with time-varying delays,Chaos,Solitons and Fractals,2007;32:1713-1719
[83]Zhao H.Y,Wang G.L.,Existence of periodic oscillatory solution of reaction -diffusion neural networks with delays, Physics Letter A, 2005;343,378-382.
[84]Singh V, Robust stability of cellular neural networks with delay: linear matrix inequality approach, IEE. Proc.Control Theory Appl.,2004;151:125-129.
[85]Chua LO, Yang L, Cellular neural networks theory, IEEE.Trans.Circuits Syst.1988; 35:1257-1272.
[86]Cao JD,Wang L, Global asymptotic stability of recurrent neural networks with Lipschitz-continuous activation functions and time-varying delays,IEEE Trans. Circuits Syst.,2003; 50:34-44.
[87]Arik S, Global robust stability of delayed neural networks, IEEE Trans.Circuits Syst., 2003; 50:156-160.
[88]Roska T, Detecting simple motion using cellular neural networks, Proc.IEEE. Int. Workshop on Cellular Neural Networks and their Applications, 1990; 127-128.
[89]Zhao HY, Global exponential stability and periodicity of cellular neural networks with variable delays, Physics Letters A, 2005; 336:331-341.
[90]Orlov YV, Utkin VI, Sliding mode control in undefinite dimensional systems, Automatica, 1987; 23(6):753-757
[91]Liao XF, Noval robust stability criteria for interval-delayed Hopfield neural networks, IEEE Trans.Circuits Syst., 2001; 48:1355-1359.
[92]Xie YF, Gui WH, Jiang ZH, Decentralized robust H-infinity descriptor output feedback control for value-bounded uncertain descriptor large scale systems, CT&A, 2006;4(2):193-200.
[93]Wang ZD, Liu YR, Yu L, Liu XY, Exponential stability of delayed recurrent neural networks with Markovian jumping parameters, Physics LettersA,2006;356:346-352.
[94]Wang LS, Xu DY, Asymptotic behavior of a class of reaction-diffusion equations with delays, J. Math. Anal.Appl, 2003;281:439-453.
[95]Temam R, Infinity-Dimensional Dynamical Systems in Mechanics and Physics, Springer-Verlag,New York,1997.
[96]Boyd SP,Ghaoui LF, Feron F, Balakrishnan V, Linear Matrix Inequalities in Systems and Control Theory,SIAM Philadelphia,PA,1994.
[97]Scoretti C, Duc G, An LIM approach to approach to decentralized H∞control,Int. [J]Control,2001,74(6):211-22.
[98]Hale JK, Theory of Functional Differential Equations, Spriger-Verlag, New York,Inc,1977.
[99] Booker L. Improving search in genetic algorithms. In Davis,L.,editor,Genetic Algorithms and Simulated Annealing,Morgan Kaufmann Publishers,san Francisco
[100]McCormick W T,Schweitzer P J.Problem decomposition and data recorganization by a cluster technique.Operation Rearch,1972,20(5):993-1009.
[101]Michalewicz Z,Genetic Algorithms+Data Structures=Evolution Programs. Berlin, Germany:Springer-Verlag,1996.
[102]Holland J H“Adaptation in Natural and Artificial Systems”,Ann Arbor,MI: University of Michigan Press,1975.
[103]Goldberg D E.“Genetic algorithms in Search,Optimization and Machine Learning, Reading”,MA:Addison-Wesley,1989.
[104]何新贵,梁久祯.利用目标函数梯度的遗传算法.软件学报,2001,12(7):245-249.
[105]陶卿,曹进德,孙德敏等.基于约束区域神经网络的动态遗传算法.软件学报.2001,12(3):462-467.
[106]刘勇,康立山,陈毓屏.非数值并行算法-遗传算法.北京:科学出版社,2003.
[107]玄光男,程润伟.遗传算法与工程优化.北京:清华大学出版社,2003.
[108]Henrik Hautop Lund.Adaptive Approaches Towards Better GA Performance inDynamic Fitness Landscapes.Technical Repot DAIMI PB-487,Aarhus University,Aarhus.
[109]Holland J.Adaptation in Natural and Artifical Systems.University of Michigan Press,Ann Arbor,MI,1975:MIT Press,Cambridge,MA,1992.
[110]Goldberg,D.E,Genetic Algorithmsin Search,Optimization and Machine Learning. Addison Wesley,Reading.MA,1989.
[111]Davis T .E. and Principe J.C.A simulated annealing Like Convergence theory for the Simple Genetic Algorithm,in Proceedings of the 4th ICGA,CA,Morgan Kaufmann, 174-181,1991.
[112]Rudolph G. Convergence Analysis on Canonical Genetic algorithms,IEEE Transaction on Neural Networks,Vol.5,NO.1,1994.
[113]王正志,薄涛,进化计算,长沙:国防科技大学出版社,2000.
[114]石玉,提高实数遗传算法数值优化效率的研究,南京航空航天大学博士学位论文,2002
[115]Maza M.D.L, and Tidor B. An Analysis of Selection Procedures with Particular Attention Paid to Proportional and Boltzmann Selection. Proceeding of the 5th ICGA, San Mateo,Morgan Kaufmann,124~131,1993.
[116]Schwefel H.P., Numerical Optimization of Computer Model, Chichester,UK,1981.
[117]GOLDBERG D E. Genetic Algorithms in Search,Optimization and Machine Learning[M]. Reading,Ma:Addison Wesley,1989.
[118]ONDREJ H, ANNA K.Improvements of real coded genetic algorithms based on differential operators preventing premature convergence[J].Advances in Engineering Software,2004,35(1):237–246.
[119]LI H,JIAO Y C,WANG Y P.Integrating the simplified quadratic interpolation into the genetic algorithm for solving constrained optimization problems[C] Proc of Int Conf on Computational Intelligence and Security.Germany:Springer,2005, 1:247–254.
[120]ONDREJ H, ANNA K. Improvements of real coded genetic algorithms based on differential operators preventing premature convergence[J].Advances in Engineering Software,2004,35(1):237-246.
[121]WANG H F, WU K Y. Hybrid genetic algorithm for optimization problems with permutation property[J]. Computers & Operations Research,2004, 31(4): 2453–2471.
[122]黄鹍,陈森发,周振国.基于正交试验法的小生境混合遗传算法[J].控制理论与应用,2004,21(6):1007-1010.
[123]李宏,焦永昌,张莉,王宇平.一种求解全局优化问题的新混合遗传算法.控制理论与应用,2007年6月,24(3):344-348.
[124]任子武,伞冶.实数遗传算法的改进及性能研究,电子学报,200年2月,35(2):270-274
[125]王凌,智能优化算法及其应用,2001年,清华大学出版社.
[126]张昀,进化速率的研究与进化理论的统一[J].北京大学学报(自然科学版),1997,33 (6):794 - 803.
[127]ALI M M,VITANEN S. A numerical comparison of some modified controlled random search algorithms[J].Journal of Global Optimization,1997,11(4):377–385.
[128]赵辉,刘鲁源,张更新.基于复合适应度微粒群算法神经网络训练,控制与决策,2005,20(8):958-960.
[129]肖本贤,昂卫兵,王群京.用混合遗传算法实现神经网络快速训练,合肥工业大学学报. 2001,24(5):901—906.
[130]Stanley K O, Miikkulainen R. Evolving neural networks through augmenting topologies [J],Evolutionary Com putation, 2002,10(2):99-127.
[131]Tsoy Y R, Sp itsyn V G. Using genetic algorithm with adaptive mutation mechanism for neural networks design andtraining[C],Proceedings of 9th Korea Russia International Symposium on Science and Technology KORUS22005, Novosibirsk, 2005: 709-714.
[132]Angeline P J,Saunders GM, Pollack J B.An evolutionary algorithm that constructs recurrent neural networks [J] ,IEEE Transactions on Neural Networks, 1994,5(1):54-65.
[133]Yao X,Liu Y. Ensemble st ructure of evolutionary artificial neural networks [A].Proceedings of IEEE International Conference on Evolutionary Computation [C].Nagoya,Japan,1996.659-664.
[134]Zhang B T,Veenker G. Neural networks that teach themselves through genetic discovery of novel examples [A].IEEE International J oint Conference on Neural Networks [C].Seattle,USA,1991,1:690-695.
[135]张丽平:粒子群优化算法的理论及实践,浙江大学博士论文,2005年1月.
[136]曾建潮,崔志华:微粒群算法的统一模型及分析,计算机研究与发展[J],2006年1月,43(1):96-100
[137]Qian Zhang, Mahdi Mahfouf, A New Structure For Particle Swarm Optimation Applicable to Single Objective and Multiobjective Problems, 3rd International IEEE Conference Intelligent System,September 2006:176-181
[138]Jonies J A, Houck R C.On the Use of Non-stationary Penalty Functions to Solve Nonlinear Constrained Optimization Problems with GAs[C]. In: Proc IEEE Int of Evol Comp, 1994:579-585
[139]Van den Bergh F. Analysis of Particle Swarm Optimizers. PH.D thesis. university of Pretoria,Nov.2001.
[140]Fogel D Ban Introduction to Simulated Evolutionary Optimization [J].IEEE Trans on Neural Networks, 1994;5(1):3-14.
[141]Kennedy J.Elberhart R C.Particule Swarm Optimization[C].In: Proc IEEE Int Confof Neural Networks, Piscataway, NJ,1995:1942-1948
[142]Parsopoulos K. E.Stretching Technque for Obtaining Global Minimizes Through Particle Swarm Optimization[C].In:Proc Particle Workshop, Indianpolis(IN), USA, 2001;22-29
[143]Parsopoulos K E.Initializing the Particles Swarm Optimizer Using the Nonlinear Simplex Method[C].In: Advanced in Intelligent Systems, Fuzzy System, Evolutionary Computation.WSEAS Press,2002:216-221
[144]Parsopoulus K E, Parsopoulus M N. Modification of the Particle Swarm Optimizer for Locating All the Global Minima, Artificial Neural Networks and Genetic Algorithm[M].Springer,2001:324-327
[145]Kennedy J,Eberhart R C. Swarm Intelligence[M]. Morgan Kaufmann 2001.
[146]Jonies J A, Houck R C.On the Use of Non-stationary Penalty Functions to Solve Nonlinear Constrained Optimization Problems with GA’s[C]. In: Proc IEEE Int of Evol Comp,1994:579-585.
[147]Van den Bergh F. Analysis of Particle Swarm Optimizers. PH.D thesis. University of Pretoria,Nov.2001.
[148]Fogel D Ban Introduction to Simulated Evolutionary Optimization [J].IEEE Trans on Neural Networks, 1994;5(1):3-14.
[149]Kennedy J.Elberhart R C.Particule Swarm Optimization[C].In: Proc IEEE Int Conf of Netral Networks,Piscataway,NJ,1995:1942-1948.
[150]Parsopoulos K. E.Stretching Technque for Obtaining Global Minimizes Through Particle Swarm Optimization[C].In:Proc Particle Workshop,Indianpolis(IN),USA, 2001;22-29.
[151]Parsopoulos K E.Initializing the Particles Swarm Optimizer Using the Nonlinear Simplex Method[C].In: Advanced in Intelligent Systems, Fuzzy System, Evolutionary Computation.WSEAS Press,2002:216-221.
[152]Parsopoulus K E, Parsopoulus M N. Modification of the Particle Swarm Optimizer for Locating All the Global Minima,Artificial Neural Networks and Genetic Algorithm[M].Springer,2001:324-327.
[153]Kennedy J,Eberhart R C. Swarm Intelligence[M]. Morgan Kaufmann 2001.
[154]谢晓峰,张文俊,杨之廉:粒子群算法综述[J].控制与决策,2003,18(2):129-134.
[155]曾建潮,介婧,崔志华:微粒群算法,科学出版社,2004年5月,北京.
[2]丁永生,计算智能——理论、技术与应用,北京:科学出版社,2004.
[3]刑文训,谢金星,现代优化计算方法,北京:清华大学出版社,2005.
[4]王凌,智能优化算法及其应用,北京:清华大学出版社,施普林格出版社,2001.
[5]阎平凡,张长水,人工神经网络与模拟进化计算,北京:清华大学出版社,2000.
[6] Hebb D O.The Organization of Behavior.New York:Wiley,1949.
[7] Eccles J C. Cholinergic and Inhibitory Synapses in A Pathway from Motor-axon Collaterals to Motorneurones. Journal physiology,1954,12(6):524.
[8] Rosenblatt F. The Perception: A Probablistic Model for Information storage and Organization in the Brain. Psychological Review,1958,23(68):386-408.
[9] Windrow B,Hoff M E,Adaptive Switching Ciruits.1960 IRE WESCON convention record:part 4. Computers:Man-Machine Systems,Losangles:96-104.
[10]Grossberg S,On the Serial Learning of Lists.Bio-science,1969,17(4):201-253.
[11]Grossberg S,Some Networks that Can Learn,Remember and Reproduce any Number of Compialted Space-time Patterns,II,stud Applied Mathematics 1970,4(49):135-166.
[12]Willshaw D J,Buneman O P,Longuest-higgins.HC Nature,1969,22(2):960.
[13]Nilsson,J,Learning chines:Foundations of Trainable Pattern Classifying, systems.McGraw-hill,New York,1965.
[14]Stein R B,Leung K V,Mangeron D,Oguztoreli M N,Improved Neuraonal models for Studying Neural Networks Kybernetik,1974,19(15):1-9.
[15]Heiden U.Ander,Existence of Periodic Solutions of a Nerve Equation.Biology Cybernitics,1976,23(21):37-39.
[16]Hopfield J J.Neural Networks and physical systems with emergent collective computational abilities.Proc Nat Acad Sci,1982,79:2554-2558.
[17]Marr D,Vision[M].San Francisco:WHF Freeman,1982.
[18]Kirkpatrick S,Gellat K C D,Veechi M P,Optimization by Simulated Annealing,Science,1983,220(4598):671-681
[19]Hinton G E,Sejuowshi T J,Ackley D H,Boltzmann Machines:Cotraint Satisfaction Networks that Learn.Carnegiemellon University,Tech,Report CMU-CS-84-119.1984.
[20]Piggio T,Analog model of Computation for III-posed Problems of Early Vision.Artificial Intelligence Lab Memo,783,MIT,1984.
[21]Poggio,T.Comtational Visionand Regularization Theory. Nature (Lond), 1985, 27(3):314-319
[22]Chua L O,Yand L.Celluar Neural networks:Theory.IEEE Transaction on Circuits and Systems,1988,35(10):1257-1272.
[23]Chua L O,Yand L,Celluar Neural Networks:Application,IEEE Transaction on Circuits and Systems,1988,35(10):1273-1290.
[24]Kosko,B.Adaptive Bidirectional Associative Memories.Applied Optical, 1987, 26(23):4647-4680.
[25]Kosko B,Bidirectional Associative Memories.IEEE Transaction On Man,System andCybernitics.1988,18(1):49-59.
[26]廖晓昕,细胞神经网络的数学理论(I)(II)。中国科学( A辑),1994, 24 (9):902-910:1037-1046.
[27]Qinghua Zhang and Albert Benveniste,Wavelet Networks,IEEE Transaction on Neural Networks,1992,3(6).889-898.
[28]P.S.Sastry,G.Santharam and K.P.Unnikrishnan,Memory Neuron Networks for Identification and Control of Dynamical systems.IEEE Transaction on Neural Networks,1994,5(2):306-319107
[29]Jenkins B K,A R Tanguay Jr,Optical Architectures for Neural Network Implementation,Handbook of Neural Computing and Neural Networks.MIT Press, Boston,1995:673-677.
[30]McAulay A D,Wand J,Ma C,Optical Heteroassciative Memory Using Spatial Light Rebroadcasters.Applied Optical,1990,29(14):2067-2073.
[31]Narendra K,Parthasarathy K,Identification and Control of Dynamical System Using Neural Networks.IEEE Transaction On Neural Networks,March 1990,1(1):4-27.
[32]Miller W T,Real time Application of Neural Networks for Sensor based Control of Robots.With Vision.IEEE Transaction On Man,System and Cybernitics 1989,23(19):825-831.
[33]Bulsari A,Some Analytical Solutions to the General Approximation Problem for Feedforword Neural Networks.Neural Networks,1993,(6):991-996.
[34]Aibara K, Chaotic Neural Networks.Physical Letter A, 1990,144(6,7):334-3340.
[35]Inoue M, Nagayoshi A., A Chaos Neuro-computer.Physical Letter A, 1991,158 (8):373-376.
[36]Inoue M,Nakamoto K.,Epilepsyina Chaos Neuro-computer Model.SPIEVOL,236,Chaos in Biology and Medicine,1993,77-84.
[37]Jokinen Petri A.On the relations between radial basis function networks and fuzzy system.In:Proceeding of INCNN’29,Vol.1, New York: IEEE, 1992, 1220-1225.
[38]Okada Hiroyuki,Initializing multilayer neural networks with fuzzy logic.In:Proceeding of INCNN’92,Vol.1, 1239-1244.42.
[39]Cai Yaling, Hon Keung Kwan,A fuzzy neural networks with fuzzy classification. In: Proceedings of ASMESCI’94, Wuhan: Process of Huazhong University of Science and Technology,1994:894~899.
[40]B E.Using spectral techniques for improved performance in ANN, Proc IEEE, 1993. 500-505.
[41]沈艳军,多输出神经元模型的多层前向神经,博士学位论文,华中科技大学,武汉,2004年10月.
[42]Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edition. Prentice Hall PTR,1998.
[43]Amari, S.,Nurata, N.: Information geometry. New York: AMS and Oxford University Press,2000.
[44]Amari, S.: Differential geometrical methods in statistics. Springer Lecture Notes in Statistics, New York; Springer-Verlag. 28(1985).
[45]Amari, S.: Differential geometry of a parametric family of invertible linear systems-Riemannian metric, dual affine connections and divergence.Mathematical Systems Theory. 20 (1987) 53-82.
[46]Amari, S.: Information geometry of EM and em algorithm for neural networks. Neural Networks. 8(9) (1995) 1379-1408.
[47]Amari, S., Kurata, K., Nagaoka, H.: Information geometry of Boltzmann machine. IEEE Trans. On Neural Networks. 3(2) (1992) 260-271.
[48]Amari,S.: Dualistic geometry of the manifold of higher-order neurons . Neural Networks. 4(4) (1991) 433-451.
[49]Amari, S., Murata, N.: Statistical theory of learning curves under entropic loss criterion. Neural Computation. 5(1992) 140-153.
[50]时小虎,Elman神经网络与进化算法的若干理论研究及应用,吉林大学博士学位论文,2006年6月。
[51]Hagan,M.T,Demuth H.B.and Beale M.Neural Network Design.Thomson Learning, USA, 1996.
[52]Widrow B,et al.Neural Networks Application in Industry.Business and Science. Communication of the ACM,1994,37:93-105.
[53]Fu L.M.An expert network for DNA sequence analysis.IEEE Intelligent Systems&Their Applications,1999,14(1):65-71.
[54]Campos M.and Lopez D.,Neural network approach to locate motifs in biosequences.Progress in Pattern Recognition,Image Analysis and Applications, Proceedings 3773,214-221(2005).
[55]Armano G.,Mancosu G.,Milanesi L.,Orro A.,Saba M.and Vargiu E.,A hybrid genetic-neural system for predicting protein secondary structure.Bmc Bioinformatics 6,(2005).
[56]Kato R.,Nakano H.,Konishi H.,Kato K.,Koga Y.,Yamane T.,Kobayashi T.and Honda H.,Novel strategy for protein exploration:High-throughput screening. assisted with fuzzy neural network.Journal of Molecular Biology 351,683-692 (2005)
[57]Coban R.and Can B.,Identification and control of ITU Triga Mark-II Nuclear Research Reactor using neural networks and fuzzy logic.Ai 2005:Advances in Artificial Intelligence 3809,1057-1062(2005).
[58]Pai P.F.and.Lin K.P,Application of hybrid learning neural fuzzy systems in reliability prediction.Quality and Reliability Engineering International 22, 199-211(2006).
[59]Guo H.J.,Lin S.F.and Liu J.H.,A radial basis function sliding mode controller for chaotic Lorenz system.Physics Letters A 351,257-261(2006).
[60]Liu Y.G.and Li Y.M.,Sliding mode adaptive neural-network control for nonholonomic mobile modular manipulators.Journal of Intelligent&Robotic Systems 44,203-224(2005).
[61]Sadjadian H.and Taghirad H.D.,Comparison of different methods for computing the forward kinematics of a redundant parallel manipulator.Journal of Intelligent&Robotic Systems 44,225-246(2005).
[62]Yildirim S.,Design of adaptive robot control system using recurrent neural network.Journal of Intelligent&Robotic Systems 44,247-261(2005).
[63]Li Y.,Liu G.,Hong T.and Liu K.,Robust control of a two-link flexible manipulator with quasi-static deflection compensation using neural networks.Journal ofIntelligent&Robotic Systems 44,263-276(2005).
[64]Tudoroiu,Patel R.and Khorasani K.,Neural network based control strategies fo N.r improving plasma characteristics in reactive ion etching. Neurocomputing 69,786-802(2006).
[65]Kim K.J.,Artificial neural networks with evolutionary instance selection for financial forecasting.Expert Systems with Applications,2006,30(3):519-526.
[66]Enke D.and Thawornwong S.,The use of data mining and neural networks for forecasting stock market returns.Expert Systems with Applications,2005,29(4): 927-940.
[67]Cao Q.,Leggio K.B.and Schniederians M.J.,A comparison between Fama and French's model and artificial neural networks in predicting the Chinese stock market.Computers&Operations Research, 2005,32(10):2499-2512.
[68]Huang W., Nakamori Y.and Wang S.Y.,Forecasting stock market movement direction with support vector machine. Computers & Operations Research, 2005,32(10):2513-2522.
[69]Armano G., Marchesi M.and Murru A.,A hybrid genetic-neural architecture for stock indexes forecasting.Information Sciences,2005,170(1):3-33.
[70]Kung S.Y.,et al.Neural Networks for Intelligent Multimedia Processing.Proc IEEE,1998, 86:1244-1272.
[71]Lang, S.: Differentail and Riemannian Manifolds. Springer-Veriag, New York. (1996).
[72]Hopfield,J.,Neural networks and physical system with emergent collective computational abilities. Proc. Nat. Acad. Sci., USA. 79 (1982) 2554-2558.
[73]Wang, L., Xu, D.: Global asymptotic stability of bidirectional associative memory neural networks with Stype distributed delays. International Journal of Systems Science. 33(11) (2002) 867-877.
[74]Wang, L., Xu, D.: global exponential stability of Hopfield reaction-diffusion neural networks with time-varying delays. Science in China (Series F). 46(6) (2003) 466-474.
[75]Wang LS, Gao YY, Global exponential robust stability of reaction-diffusion interval neural networks with time-varying delays, Physics Letters A, 2006; 350:342-348.
[76]Wang LS, Xu DY, Global exponential stability of Hopfield reaction-diffusion neural networks with time-varying delays, Science in China (Series F), 2003; 46(6):466-474.
[77]Liao XX, Fu YL, Gao J, Zhao ZQ, Stability of Hopfield neural networks with reaction -diffusion terms, Acta Electronica Sinica, 2000; 28:78-80.
[78]Edward R.D, Approximation of neural network dynamics by reaction-diffusion, Methods in the Applied Siences, 1998; 19(6):651-677.
[79]Luo X.Y, Cui B.T, Boundedness and exponential stability for nonautonomous cellular neural networks with reaction-diffusion terms, Chaos,Solitons and Fractals, 2007; 33:635-662.
[80]Song Q.K, Cao, J.D, Global exponential stability and existence of periodic solutions in BAM network with delays and reaction-diffusion terms,Chaos,Solitons and Fractals,2005,23:421-430.
[81]Cui B.T,Luo X.Y, Global exponential stability of BAM neural networks with distributed delays and reaction-diffusion terms, Chaos, Solitons and Fractals , 2006; 27:1347-1354.
[82]Zhou Q.G,Wan L,Sun J. H,Exponential stability of reaction-diffusion generalized Cohen-Grossberg neural networks with time-varying delays,Chaos,Solitons and Fractals,2007;32:1713-1719
[83]Zhao H.Y,Wang G.L.,Existence of periodic oscillatory solution of reaction -diffusion neural networks with delays, Physics Letter A, 2005;343,378-382.
[84]Singh V, Robust stability of cellular neural networks with delay: linear matrix inequality approach, IEE. Proc.Control Theory Appl.,2004;151:125-129.
[85]Chua LO, Yang L, Cellular neural networks theory, IEEE.Trans.Circuits Syst.1988; 35:1257-1272.
[86]Cao JD,Wang L, Global asymptotic stability of recurrent neural networks with Lipschitz-continuous activation functions and time-varying delays,IEEE Trans. Circuits Syst.,2003; 50:34-44.
[87]Arik S, Global robust stability of delayed neural networks, IEEE Trans.Circuits Syst., 2003; 50:156-160.
[88]Roska T, Detecting simple motion using cellular neural networks, Proc.IEEE. Int. Workshop on Cellular Neural Networks and their Applications, 1990; 127-128.
[89]Zhao HY, Global exponential stability and periodicity of cellular neural networks with variable delays, Physics Letters A, 2005; 336:331-341.
[90]Orlov YV, Utkin VI, Sliding mode control in undefinite dimensional systems, Automatica, 1987; 23(6):753-757
[91]Liao XF, Noval robust stability criteria for interval-delayed Hopfield neural networks, IEEE Trans.Circuits Syst., 2001; 48:1355-1359.
[92]Xie YF, Gui WH, Jiang ZH, Decentralized robust H-infinity descriptor output feedback control for value-bounded uncertain descriptor large scale systems, CT&A, 2006;4(2):193-200.
[93]Wang ZD, Liu YR, Yu L, Liu XY, Exponential stability of delayed recurrent neural networks with Markovian jumping parameters, Physics LettersA,2006;356:346-352.
[94]Wang LS, Xu DY, Asymptotic behavior of a class of reaction-diffusion equations with delays, J. Math. Anal.Appl, 2003;281:439-453.
[95]Temam R, Infinity-Dimensional Dynamical Systems in Mechanics and Physics, Springer-Verlag,New York,1997.
[96]Boyd SP,Ghaoui LF, Feron F, Balakrishnan V, Linear Matrix Inequalities in Systems and Control Theory,SIAM Philadelphia,PA,1994.
[97]Scoretti C, Duc G, An LIM approach to approach to decentralized H∞control,Int. [J]Control,2001,74(6):211-22.
[98]Hale JK, Theory of Functional Differential Equations, Spriger-Verlag, New York,Inc,1977.
[99] Booker L. Improving search in genetic algorithms. In Davis,L.,editor,Genetic Algorithms and Simulated Annealing,Morgan Kaufmann Publishers,san Francisco
[100]McCormick W T,Schweitzer P J.Problem decomposition and data recorganization by a cluster technique.Operation Rearch,1972,20(5):993-1009.
[101]Michalewicz Z,Genetic Algorithms+Data Structures=Evolution Programs. Berlin, Germany:Springer-Verlag,1996.
[102]Holland J H“Adaptation in Natural and Artificial Systems”,Ann Arbor,MI: University of Michigan Press,1975.
[103]Goldberg D E.“Genetic algorithms in Search,Optimization and Machine Learning, Reading”,MA:Addison-Wesley,1989.
[104]何新贵,梁久祯.利用目标函数梯度的遗传算法.软件学报,2001,12(7):245-249.
[105]陶卿,曹进德,孙德敏等.基于约束区域神经网络的动态遗传算法.软件学报.2001,12(3):462-467.
[106]刘勇,康立山,陈毓屏.非数值并行算法-遗传算法.北京:科学出版社,2003.
[107]玄光男,程润伟.遗传算法与工程优化.北京:清华大学出版社,2003.
[108]Henrik Hautop Lund.Adaptive Approaches Towards Better GA Performance inDynamic Fitness Landscapes.Technical Repot DAIMI PB-487,Aarhus University,Aarhus.
[109]Holland J.Adaptation in Natural and Artifical Systems.University of Michigan Press,Ann Arbor,MI,1975:MIT Press,Cambridge,MA,1992.
[110]Goldberg,D.E,Genetic Algorithmsin Search,Optimization and Machine Learning. Addison Wesley,Reading.MA,1989.
[111]Davis T .E. and Principe J.C.A simulated annealing Like Convergence theory for the Simple Genetic Algorithm,in Proceedings of the 4th ICGA,CA,Morgan Kaufmann, 174-181,1991.
[112]Rudolph G. Convergence Analysis on Canonical Genetic algorithms,IEEE Transaction on Neural Networks,Vol.5,NO.1,1994.
[113]王正志,薄涛,进化计算,长沙:国防科技大学出版社,2000.
[114]石玉,提高实数遗传算法数值优化效率的研究,南京航空航天大学博士学位论文,2002
[115]Maza M.D.L, and Tidor B. An Analysis of Selection Procedures with Particular Attention Paid to Proportional and Boltzmann Selection. Proceeding of the 5th ICGA, San Mateo,Morgan Kaufmann,124~131,1993.
[116]Schwefel H.P., Numerical Optimization of Computer Model, Chichester,UK,1981.
[117]GOLDBERG D E. Genetic Algorithms in Search,Optimization and Machine Learning[M]. Reading,Ma:Addison Wesley,1989.
[118]ONDREJ H, ANNA K.Improvements of real coded genetic algorithms based on differential operators preventing premature convergence[J].Advances in Engineering Software,2004,35(1):237–246.
[119]LI H,JIAO Y C,WANG Y P.Integrating the simplified quadratic interpolation into the genetic algorithm for solving constrained optimization problems[C] Proc of Int Conf on Computational Intelligence and Security.Germany:Springer,2005, 1:247–254.
[120]ONDREJ H, ANNA K. Improvements of real coded genetic algorithms based on differential operators preventing premature convergence[J].Advances in Engineering Software,2004,35(1):237-246.
[121]WANG H F, WU K Y. Hybrid genetic algorithm for optimization problems with permutation property[J]. Computers & Operations Research,2004, 31(4): 2453–2471.
[122]黄鹍,陈森发,周振国.基于正交试验法的小生境混合遗传算法[J].控制理论与应用,2004,21(6):1007-1010.
[123]李宏,焦永昌,张莉,王宇平.一种求解全局优化问题的新混合遗传算法.控制理论与应用,2007年6月,24(3):344-348.
[124]任子武,伞冶.实数遗传算法的改进及性能研究,电子学报,200年2月,35(2):270-274
[125]王凌,智能优化算法及其应用,2001年,清华大学出版社.
[126]张昀,进化速率的研究与进化理论的统一[J].北京大学学报(自然科学版),1997,33 (6):794 - 803.
[127]ALI M M,VITANEN S. A numerical comparison of some modified controlled random search algorithms[J].Journal of Global Optimization,1997,11(4):377–385.
[128]赵辉,刘鲁源,张更新.基于复合适应度微粒群算法神经网络训练,控制与决策,2005,20(8):958-960.
[129]肖本贤,昂卫兵,王群京.用混合遗传算法实现神经网络快速训练,合肥工业大学学报. 2001,24(5):901—906.
[130]Stanley K O, Miikkulainen R. Evolving neural networks through augmenting topologies [J],Evolutionary Com putation, 2002,10(2):99-127.
[131]Tsoy Y R, Sp itsyn V G. Using genetic algorithm with adaptive mutation mechanism for neural networks design andtraining[C],Proceedings of 9th Korea Russia International Symposium on Science and Technology KORUS22005, Novosibirsk, 2005: 709-714.
[132]Angeline P J,Saunders GM, Pollack J B.An evolutionary algorithm that constructs recurrent neural networks [J] ,IEEE Transactions on Neural Networks, 1994,5(1):54-65.
[133]Yao X,Liu Y. Ensemble st ructure of evolutionary artificial neural networks [A].Proceedings of IEEE International Conference on Evolutionary Computation [C].Nagoya,Japan,1996.659-664.
[134]Zhang B T,Veenker G. Neural networks that teach themselves through genetic discovery of novel examples [A].IEEE International J oint Conference on Neural Networks [C].Seattle,USA,1991,1:690-695.
[135]张丽平:粒子群优化算法的理论及实践,浙江大学博士论文,2005年1月.
[136]曾建潮,崔志华:微粒群算法的统一模型及分析,计算机研究与发展[J],2006年1月,43(1):96-100
[137]Qian Zhang, Mahdi Mahfouf, A New Structure For Particle Swarm Optimation Applicable to Single Objective and Multiobjective Problems, 3rd International IEEE Conference Intelligent System,September 2006:176-181
[138]Jonies J A, Houck R C.On the Use of Non-stationary Penalty Functions to Solve Nonlinear Constrained Optimization Problems with GAs[C]. In: Proc IEEE Int of Evol Comp, 1994:579-585
[139]Van den Bergh F. Analysis of Particle Swarm Optimizers. PH.D thesis. university of Pretoria,Nov.2001.
[140]Fogel D Ban Introduction to Simulated Evolutionary Optimization [J].IEEE Trans on Neural Networks, 1994;5(1):3-14.
[141]Kennedy J.Elberhart R C.Particule Swarm Optimization[C].In: Proc IEEE Int Confof Neural Networks, Piscataway, NJ,1995:1942-1948
[142]Parsopoulos K. E.Stretching Technque for Obtaining Global Minimizes Through Particle Swarm Optimization[C].In:Proc Particle Workshop, Indianpolis(IN), USA, 2001;22-29
[143]Parsopoulos K E.Initializing the Particles Swarm Optimizer Using the Nonlinear Simplex Method[C].In: Advanced in Intelligent Systems, Fuzzy System, Evolutionary Computation.WSEAS Press,2002:216-221
[144]Parsopoulus K E, Parsopoulus M N. Modification of the Particle Swarm Optimizer for Locating All the Global Minima, Artificial Neural Networks and Genetic Algorithm[M].Springer,2001:324-327
[145]Kennedy J,Eberhart R C. Swarm Intelligence[M]. Morgan Kaufmann 2001.
[146]Jonies J A, Houck R C.On the Use of Non-stationary Penalty Functions to Solve Nonlinear Constrained Optimization Problems with GA’s[C]. In: Proc IEEE Int of Evol Comp,1994:579-585.
[147]Van den Bergh F. Analysis of Particle Swarm Optimizers. PH.D thesis. University of Pretoria,Nov.2001.
[148]Fogel D Ban Introduction to Simulated Evolutionary Optimization [J].IEEE Trans on Neural Networks, 1994;5(1):3-14.
[149]Kennedy J.Elberhart R C.Particule Swarm Optimization[C].In: Proc IEEE Int Conf of Netral Networks,Piscataway,NJ,1995:1942-1948.
[150]Parsopoulos K. E.Stretching Technque for Obtaining Global Minimizes Through Particle Swarm Optimization[C].In:Proc Particle Workshop,Indianpolis(IN),USA, 2001;22-29.
[151]Parsopoulos K E.Initializing the Particles Swarm Optimizer Using the Nonlinear Simplex Method[C].In: Advanced in Intelligent Systems, Fuzzy System, Evolutionary Computation.WSEAS Press,2002:216-221.
[152]Parsopoulus K E, Parsopoulus M N. Modification of the Particle Swarm Optimizer for Locating All the Global Minima,Artificial Neural Networks and Genetic Algorithm[M].Springer,2001:324-327.
[153]Kennedy J,Eberhart R C. Swarm Intelligence[M]. Morgan Kaufmann 2001.
[154]谢晓峰,张文俊,杨之廉:粒子群算法综述[J].控制与决策,2003,18(2):129-134.
[155]曾建潮,介婧,崔志华:微粒群算法,科学出版社,2004年5月,北京.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |