人工神经网络的泛化性能与降水预报的应用研究
|
摘要
人工神经网络是一种模拟人脑信息处理方法的非线性系统，具有较强的处理非线性问题的能力，比较适合于一些信息复杂、知识背景不清楚和推理规则不明确问题(如短期降水预报问题)的建模。随着神经网络方法在大气科学领域研究的不断深入，研究人员发现神经网络方法在实际天气预报业务应用中存在一个重要的问题一人工神经网络预报模型泛化性能问题。该问题的研究不仅关系到在大气学科中能否进一步深入开展有关人工神经网络方法的预报业务应用，并且也是目前人工神经网络应用理论研究中尚未得到很好解决的关键技术问题。人工神经网络的理论和应用研究表明，网络的泛化性能与网络的结构、网络的参数和样本的质量密切相关。然而，对于某个具体的短期天气预报神经网络模型，在建模过程中如何确定适合的网络结构，如何优化网络参数，使建立的神经网络模型具有较好的泛化性能却是一个难题，目前，通常采用的方法是通过反复试验来确定网络的结构和各种参数，而这样，往往会导致网络出现过拟合问题，从而严重影响网络的泛化能力。
在采用神经网络方法进行实际的气象预报应用时，由于目前在国内外的神经网络预报建模理论方法研究中，尚未有确定神经网络预报模型的网络结构的客观定量方法，并且网络模型的训练次数(网络模型对训练样本的拟合精度)变化对预报模型的泛化性能有重要影响，因此，如何客观确定最适宜的网络结构，提高神经网络预报模型的泛化性能问题，不仅是目前人工神经网络预报建模理论需要深入研究的科学问题，也是目前利用人工神经网络方法进行业务天气预报应用最迫切需要解决的核心技术。
针对在短期天气预报神经网络建模过程中难于确定网络的结构和优化网络参数的问题，本文提出了利用遗传算法优化神经网络的连接权和网络结构，并在遗传进化过程中采取保留最佳个体，从而客观确定短期天气预报神经网络模型的网络结构方法。并以广西区域降水短期预报神经网络模型和南海西行台风强度短期预报神经网络模型为例进行研究，有以下主要的结论：
(1)用遗传算法优化神经网络的连接权、网络结构，并在进化过程中采取保留最佳个体的方法，解决了由于神经网络初始权值的随机性和网络结构确定过程中所带来的网络振荡，以及容易陷入局部解的问题。短期降水预报的神经网络预报模型和南海西行台风强度短期预报神经网络模型实例的计算结果表明，这种新方法避免了一般神经网络依靠经验确定网络结构的困难。
(2)用遗传算法来确定神经网络结构，优化神经网络的连接权，使神经网络具有最优的网络结构。结果表明，所建立的遗传-神经网络模型其泛化能力远优于一般的神经网络预报模型。
针对在短期天气预报神经网络建模过程中训练样本的复杂性影响神经网络的泛化性能问题，本文进一步通过研究网络模型学习矩阵的复共线性关系对预报模型泛化能力的影响，提出了采用主成分分析(PAC)建立神经网络学习矩阵的新方法，以消除学习矩阵的复共线性关系，有效地避免神经网络过拟合现象的出现，从而提高神经网络的泛化性能。并以广西区域短期降水预报为例进行神经网络建模，结果发现，在预报模型输入节点相同的情况下，较小的网络结构或网络结构增大时，无复共线性关系的神经网络预报模型与存在复共线性关系的神经网络预报模型的拟合误差变化不大，且平均拟合误差数值十分相近，但是无复共线性关系的预报模型的泛化能力明显优于存在复共线性关系的预报模型。进一步计算分析了训练次数从5000次到20000次的两种模型的泛化能力，同样表明，神经网络的学习矩阵存在复共线性关系会显著降低预报模型的预报精度。
Artificial Neural Network (ANN) is a nonlinear system that simulates theinformation processing method of the human brain, with strong ability to handlenonlinear problems, and adapts to the modeling for such problems as with complexinformation, dark background knowledge, or indefinite inference rules. With theapplication study of the NN on atmospheric science has been developed deeply, asignificant problem, i.e. the generalization capability of the ANN has been found inapplication of the ANN to the practical weather forecast operation. It is not onlyconcerned to the further application in the practical weather forecast operation, butalso a key technical problem unresolved in the application theoretic research of ANN.The application and theoretic research of ANN indicates that the generalizationcapability of the NN is closely related to the network structure, parameter and thesample quality. However, it is very difficult to decide the suitable network structure,to optimize the network parameter for better generalization capability of the ANNforecast model for a specific question. At present, the usual method to determine thestructure and network parameters is by means of repeating tests, and so, it oftenconduces to the overfitting problem, which affects the generalization ability of theNN model seriously.
Because there is no objective quantitative method to settle the NN modelstructure theoretically in application of the ANN to the practical weather forecast indomestic and foreign countries, and the change of network model training number(i.e. the fitting precision of network model for the training samples) seriously affectsthe generalization capability, therefore, how to determine objectively the mostappropriate network structure to improve the generalization capability of the NNmodel is not only a matter of researched deeply in ANN modeling, but also a keytechnology to be resolved most urgently in the ANN application to the actualweather forecast operation presently.
In view of the question that how to settle the network structure and to optimizethe network parameter, a new method is proposed in this article to determine the NN short-term weather prediction model objectively: the Genetic Algorithm (GA) wasused to optimize the connection weight and structure of the neural network, the bestindividual was retained in the genetic evolution process. Taking the Guangxiregional short-term rainfall prediction NN model and the intensity of west-forwardtyphoon short-term prediction NN model over South China Sea as examples to studyin this article, the main conclusions are as follows:
(1) Optimizing the connection weight and network structure of NN with GA,and reserving the optimum individual in the evolution computation process is amethod which is able to solve the problems of the randomicity of initial weightvalues of the NN, and the objectivity in the determination of the NN structure, whichfrequently brings about oscillations in network training, thus leading to the localsolution. The practical calculation of short-term rainfall prediction ANN modelshows that the new approach avoids the difficulty of determination of the NNstructure by experience.
(2) Making use of GA to determine the neural network structure, optimizing theconnection weight of neural network, so as to get the optimal neural networkstructure. The results show that the generalization capability of the GANN model ismuch better than the common NN model.
With the problem that the quality of the training samples affects thegeneralization capability of the ANN model in establishment of short-term weatherforecast model, the effect of the learning matrix in NN forecast model with themulti-collinearity on the generalization capability is researched further. A new way isproposed, by using the principal components analysis (PAC) to construct the NNlearning matrix, so as to avoid the multi-collinearity and to enhance the quality of thetraining sample for the purpose of improving the generalization capability. TakingGuangxi regional short-term rainfall forecast NN model as example, the resultsuggests that in the context of the same input knot number, whatever the network is,smaller or getting larger, there is few changes in simulation error for both the neuralnetwork models, which of one with multi-collinearity and other without, the meansimulation errors for both of the two types model are very close to each other, but the generalization capability of the neural network with multi-collinearity is obvioussuperior than that without multi-collinearity. Further more, analyses of thegeneralization capability for the two types of models in different training times from5000 to 20000 indicates that the multi-collinearity have the remarkable effect ondecrease the forecast precision to the neural network forecast model.
在采用神经网络方法进行实际的气象预报应用时，由于目前在国内外的神经网络预报建模理论方法研究中，尚未有确定神经网络预报模型的网络结构的客观定量方法，并且网络模型的训练次数(网络模型对训练样本的拟合精度)变化对预报模型的泛化性能有重要影响，因此，如何客观确定最适宜的网络结构，提高神经网络预报模型的泛化性能问题，不仅是目前人工神经网络预报建模理论需要深入研究的科学问题，也是目前利用人工神经网络方法进行业务天气预报应用最迫切需要解决的核心技术。
针对在短期天气预报神经网络建模过程中难于确定网络的结构和优化网络参数的问题，本文提出了利用遗传算法优化神经网络的连接权和网络结构，并在遗传进化过程中采取保留最佳个体，从而客观确定短期天气预报神经网络模型的网络结构方法。并以广西区域降水短期预报神经网络模型和南海西行台风强度短期预报神经网络模型为例进行研究，有以下主要的结论：
(1)用遗传算法优化神经网络的连接权、网络结构，并在进化过程中采取保留最佳个体的方法，解决了由于神经网络初始权值的随机性和网络结构确定过程中所带来的网络振荡，以及容易陷入局部解的问题。短期降水预报的神经网络预报模型和南海西行台风强度短期预报神经网络模型实例的计算结果表明，这种新方法避免了一般神经网络依靠经验确定网络结构的困难。
(2)用遗传算法来确定神经网络结构，优化神经网络的连接权，使神经网络具有最优的网络结构。结果表明，所建立的遗传-神经网络模型其泛化能力远优于一般的神经网络预报模型。
针对在短期天气预报神经网络建模过程中训练样本的复杂性影响神经网络的泛化性能问题，本文进一步通过研究网络模型学习矩阵的复共线性关系对预报模型泛化能力的影响，提出了采用主成分分析(PAC)建立神经网络学习矩阵的新方法，以消除学习矩阵的复共线性关系，有效地避免神经网络过拟合现象的出现，从而提高神经网络的泛化性能。并以广西区域短期降水预报为例进行神经网络建模，结果发现，在预报模型输入节点相同的情况下，较小的网络结构或网络结构增大时，无复共线性关系的神经网络预报模型与存在复共线性关系的神经网络预报模型的拟合误差变化不大，且平均拟合误差数值十分相近，但是无复共线性关系的预报模型的泛化能力明显优于存在复共线性关系的预报模型。进一步计算分析了训练次数从5000次到20000次的两种模型的泛化能力，同样表明，神经网络的学习矩阵存在复共线性关系会显著降低预报模型的预报精度。
Artificial Neural Network (ANN) is a nonlinear system that simulates theinformation processing method of the human brain, with strong ability to handlenonlinear problems, and adapts to the modeling for such problems as with complexinformation, dark background knowledge, or indefinite inference rules. With theapplication study of the NN on atmospheric science has been developed deeply, asignificant problem, i.e. the generalization capability of the ANN has been found inapplication of the ANN to the practical weather forecast operation. It is not onlyconcerned to the further application in the practical weather forecast operation, butalso a key technical problem unresolved in the application theoretic research of ANN.The application and theoretic research of ANN indicates that the generalizationcapability of the NN is closely related to the network structure, parameter and thesample quality. However, it is very difficult to decide the suitable network structure,to optimize the network parameter for better generalization capability of the ANNforecast model for a specific question. At present, the usual method to determine thestructure and network parameters is by means of repeating tests, and so, it oftenconduces to the overfitting problem, which affects the generalization ability of theNN model seriously.
Because there is no objective quantitative method to settle the NN modelstructure theoretically in application of the ANN to the practical weather forecast indomestic and foreign countries, and the change of network model training number(i.e. the fitting precision of network model for the training samples) seriously affectsthe generalization capability, therefore, how to determine objectively the mostappropriate network structure to improve the generalization capability of the NNmodel is not only a matter of researched deeply in ANN modeling, but also a keytechnology to be resolved most urgently in the ANN application to the actualweather forecast operation presently.
In view of the question that how to settle the network structure and to optimizethe network parameter, a new method is proposed in this article to determine the NN short-term weather prediction model objectively: the Genetic Algorithm (GA) wasused to optimize the connection weight and structure of the neural network, the bestindividual was retained in the genetic evolution process. Taking the Guangxiregional short-term rainfall prediction NN model and the intensity of west-forwardtyphoon short-term prediction NN model over South China Sea as examples to studyin this article, the main conclusions are as follows:
(1) Optimizing the connection weight and network structure of NN with GA,and reserving the optimum individual in the evolution computation process is amethod which is able to solve the problems of the randomicity of initial weightvalues of the NN, and the objectivity in the determination of the NN structure, whichfrequently brings about oscillations in network training, thus leading to the localsolution. The practical calculation of short-term rainfall prediction ANN modelshows that the new approach avoids the difficulty of determination of the NNstructure by experience.
(2) Making use of GA to determine the neural network structure, optimizing theconnection weight of neural network, so as to get the optimal neural networkstructure. The results show that the generalization capability of the GANN model ismuch better than the common NN model.
With the problem that the quality of the training samples affects thegeneralization capability of the ANN model in establishment of short-term weatherforecast model, the effect of the learning matrix in NN forecast model with themulti-collinearity on the generalization capability is researched further. A new way isproposed, by using the principal components analysis (PAC) to construct the NNlearning matrix, so as to avoid the multi-collinearity and to enhance the quality of thetraining sample for the purpose of improving the generalization capability. TakingGuangxi regional short-term rainfall forecast NN model as example, the resultsuggests that in the context of the same input knot number, whatever the network is,smaller or getting larger, there is few changes in simulation error for both the neuralnetwork models, which of one with multi-collinearity and other without, the meansimulation errors for both of the two types model are very close to each other, but the generalization capability of the neural network with multi-collinearity is obvioussuperior than that without multi-collinearity. Further more, analyses of thegeneralization capability for the two types of models in different training times from5000 to 20000 indicates that the multi-collinearity have the remarkable effect ondecrease the forecast precision to the neural network forecast model.
引文
[1] Fukushinma K, et al. Neocognitron: A new Algorithm for Pattern Recognition Tolerant of Deformation and Shifts in Position[J]. Pattern Recognition, 1982, 15: 455-469.
[2] John Hopfield, Tank D W. "Neural" computation of decisions of optimization problems[J]. Biol Cybern, 1985, 52(3): 141-152.
[3] Aiko Prasn. Network management achitectures [D]. CTIT Ph.D-thesis series No. 95 (02),1995.
[4] Amari S. Natural gradiant works efficiently to learning[J], Neural Computation, 1998, NO: 252-276.
[5] Atiya A, C. Ji. How initial conditions affect generalization performance in large networks[J]. IEEE Trans on neural networks. 1997, 8(2): 448-451.
[6] Bagley J.D. The behavior of adaptation system which employ genetic and correlation algorithm[J]. Dissertation abstracts international, 1967, 28(12): 34-41.
[7] Bhattacharrya S, Pendharkar PC. Inductive evolutionary and neural techniques for discri- mination[J]. Decision Sciences, 1998, (4): 71-99.
[8] De JongK. A. An analysis of the behavior of aclassof genetic adaptation system [D]. Ph.D Dissertation, University of Michigan, 1975.
[9] Dorigo M., and Schneph U., et al. Genetic-based machine learning and behavior-based robotics: a new synthesis[J]. IEEE Transactions on Systems, Man and Cybernetics, 1993, 23(1):141-154.
[10] Foresee F D, Hagan M T. Gauss-Newton approximation to Bayesian regularization[J]. In: Proceedings of the 1997 International Join Conference on Neural Networks, Houston, Texas, 1997:1930-1935.
[11] Caren Marzban, Arthur Witt. A Bayesian Neural Network for Severe-Hail Size Prediction[J]. Weather and Forecasting, 2001,16(5), 600-610.
[12] GemanS. Neural networks and bias/variance dilemma[J]. Neural Computation, 1992, (4):1-58.
[13] HORVATH G, SZABO T. CMAC neural network with improved generalization property for system modeling[A]. Instrumentation and Measurement Technology Conference 2002[C], 2002 (2):1603-1608.
[14] 袁曾任．人工神经网络及其应用[M]．北京：清华大学出版社，1999：118-131．
[15] 温熙森，胡莺庆．丘静．模式识别与状态监控[M]．长沙：国防科技大学出版社，1997， 134-150．
[16] 李敏强．遗传算法和神经网络的结合[M]．系统工程理论与实践，1999．(2)：65-69．
[17] 方剑．席裕庚．神经网络构造设计的和方法[J]．信息与控制，1996，25(3)：156-164．
[18] 阎平凡．人工神经网络的容量、学习与计算复杂性[J]．电子学报，1995．23(1)：63-67．
[19] 秦伟良，金龙．小波网络方法用于时间序列分析中非线性模型的研究[J]．南京气象学院学报，1997，20(1)：76-80．
[20] 高建芸．基于前馈网络的热带气旋短期气候预测模型[J]．气象科学，1999，1(19)：158-164．
[21] 金龙，苗春生，陈宁等．定性和定量长期预报模型的综合分析[J]．气象学报，2000，58(4)：477-483．
[22] 金龙．罗莹．李永华．长期天气的人工神经网络混合预报模型研究[J]．系统工程学报，2003，18(4)：331-336．
[23] 金龙，朱诗武．数值预报产品的神经网络释用预报应用[C]．中国神经网络学术大会，北京：电子工业出版社，1999．
[24] 罗莹．金龙．数值预报产品完全预报(PP)方法的改进．大气科学发展战略[M]，气象出版社，2002．
[25] 李永华，刘德，金龙，基于BP神经网络的汛期降水预测模型研究[J]，气象科学，2002，22(4)：461-467．
[26] J i n Long (金龙), Luo Ying (罗莹), Guo Guang (郭光) et al. Study on mixed model of neural network for farmland Flood/Drought Prediction [J]. Acta Meteorological Sinica, 1997, 11 (3): 364-373.
[27] Jin Long (金龙), Luo Ying (罗莹), Li Yonghua (李永华). Study on Prediction Modeling of the artificial neural network from the Combination of multivariate analysis and mean generat ion funct ion [C], proceedings of the 4th World Congress on intelligent Control and automation. 2002, Shanghai, China, press of east China university of Science and technology, Vol.3, 2440-2444, IEEE Catalog Number: 02EX527C.
[28] Guo Guang (郭光), Yang Shaojin (严绍瑾), Jinlong. Time series prediction model consisting of artificial neural network and genetic algorithm[J].气象学报(英文版), 1998, 12 (2): 247-256.
[29] Jin Long (金龙), Luo Ying (罗莹). Study on flood/drought prediction neuron network method Composed of time-Series Continuation and related external variables[C]. Progress in neural information Processing, HongKong, 1996, vol.2: 732-736.
[30] Jin Long (金龙),Lou Ying (罗莹) and Lin Zhenshan (林振山). Comparison of Long-term forecasting of June-August rainfall over Changjiang-Huaihe valley[J]. Advances in Atmospheric Sciences, 1997, 14(1): 87-92.
[31] Jin Long(金龙), Qing Wei Liang(秦伟良). Study on Combination of ANN method with mean generating function for Short-term Climate prediction[C], 8th International Conference on neural information processing. Shanghai, China, Fudan university Pres, 2001, vol. 2: 981-985.
[32] 白慧卿，方宗义，吴蓉璋．基于人工神经网络的GMS云图四类云系的识别[J]．应用气象学报，1998，19(4)：402-409．
[33] 白慧卿．NWP Ⅱ+及其在方法云系分类中的应用[J]．气象．1999，25(6)：27-30．
[34] 梁益同，胡江林．NOAA卫星图像水体信息神经网络识别方法的探讨[J]．应用气象学报，2001，12(1)：85-90．
[35] 梁益同，胡江林．基于神经网络的气象卫星影像森林火点自动识别的试验研究[J]．应用气象学报．2003．14(6)：708-714．
[36] 张韧，王海俊，孙照渤等．双光谱卫星云图的模糊推理云分类[J]．防灾减灾工程学报．2004，24(3)：257-263．
[37] 王继光，张韧，王彦磊等．卫星云图样本集的FCM优化调整与云类判别[J]．防灾减灾工程学报，2005，25(2)：163-167．
[38] 王彦磊，张韧，孙照渤．基于模糊C均值聚类的云图样本修正与云类自动识别[J]．海洋科学进展，2005，23(2)：219-226．
[39] 王继光，张韧，洪梅，纪飞．卫星云图分类的一种综合优化聚类方法[J]．解放军理工大学学报(自然科学版)．2005，6(6)：585-590．
[40] 洪梅，张韧，万齐林，朱伟军．模糊聚类与遗传算法相结合的卫星云图分类[J]．地球物理学进展，2005，20(4)：1009-1014．
[41] 洪梅，张韧，孙照渤．多光谱卫星云图的高维特征聚类与降水天气判别[J]．遥感学报．2006，10(2)：184-190．
[42] Donald W. McCann. A neural network short-term forecast of Significant thunderstorms, Weather and Forecasting[J], 1992,7(3):525-534.
[43] Caren Marzban, Arthur Witt. A Bayesian Neural Network for Severe-Hail Size Prediction[J], Weather and Forecasting, 2001, 16(5): 600-610.
[44] 梅钰．人工神经网络在辐射雾预报中和应用[J]．应用气象学报．1999，10(4)：511-512．
[45] Andrew R. Dean and Brian H. Fiedler. Forecasting Warm-Season Burn-off of Low Clouds at the San Francisco International Airport Using Linear Regression and a Neural Network[J]. Journal of Applied Meteorology, 2001, 41 (6): 629-639.
[46] 金龙，申双和．罗莹等．水面蒸发计算的人工神经网络方法研究[J]．南京气象学学报，1996，19(3)，342-347．
[47] 曹杰，谢应齐．预报方程时变参数的一种新递推方案[J]．大气科学，1996，21(6)：698-704．
[48] J. Shao. Improving Nowcasts of Road Surface Temperature by a Back-propagation Neural Network[J]. Weather and Forecasting, 1998, 13(1):164-171.
[49] Lei Shi. Retrieval of Atmospheric Temperature Profiles from AMSU-A Measurement Using a Neural Network Approach[J]. Journal of Atmospheric and Oceanic Technology. 2001, 18(3): 340-347.
[50] 金龙．林熙，金健等．模块化模糊神经网络的数值预报产品释用预报研究[J]．气象学报，2003，61(1)，78-84．
[51] 周曾奎，韩贵荣，朱定真等．人工神经网络台风预报系统[J]．气象，1996，22(1)：18-21．
[52] Long-Jin Baik and Hong-sub Hwang. Tropical Cyclone Intensity Prediction Using Regression Method and Neural Network[J]. Journal of the Meteorology Society of Japan, 1998, 76 (5): 711-717.
[53] 覃志年，金龙．况雪源．人工神经网络的短期气候定性预测方法研究[J]．气象科技，2004，32(3)：168-172．
[54] 李柞泳，邓新民。人工神经网络在台风预报中的应用初探[J]．自然灾害学报，1995，4(2)：86-90．
[55] 陆虹，金龙．缪启龙等．影响广西热带气旋年频数的神经网络预测模型[J]．南京气象学院学报，2003，26(1)：56-62．
[56] 张韧，蒋国荣，余志豪等．利用神经网络计算方法建立太平洋副方的预报模型[J]．应用气象学报，2000，11(4)：474-483．
[57] 张韧．基于前传式网络逼近的太平洋副热带高压活动的诊断预测[J]．大气科学，2001，25(5)：650-660．
[58] 蔡煜东，宫家文，甘骏人等。运用人工神经网络作汛期降水预报[J]．气象科学，1994，14(4)，386-389．
[59] 盛永宽．短期气象(月、季、年)逐月降水系统研究[J]．气象．1996．22(1)：3-8．
[60] 金龙，陈宁，林振山．基于人工神经网络的集成预报方法研究和比较[J]．气象学报，1999，57(2)：198-207．
[61] 郭光，严绍瑾，尹树新．人工神经网络用于我国东部汛期降水预测的研究[J]．南京气象学院学报，1996，19(3)：354-357．
[62] David Silverman, John A. Dracup. Artificial Network and Long-range Precipitation in California[J], Journal of Apllied Meteorology, 2000, 39(1): 57-66.
[63] 熊秋芬，王丽．湖北省常规天然要素分县MOS预报效果检验[J]．湖北气象，2000，(4)：13-16．
[64] JIN Long, KONG Xueyuan, HUANG Haihong. Study on the Overfitting of the Artificial Neural Network Forecasting Model[J]. ACTA METEOROLOGICA SINCA, 2005, 19(2): 216-225.
[65] 胡江林，张礼平，宇如聪．神经网络模型预报湖北汛期降水量的应用研究[J]．气象学报，2001，59(6)：776-783．
[66] 金龙，罗莹，王业宏．月降水量的神经网络混合预报方法[J]．高原气象，2003．22(6)：618-623．
[67] 王业宏，金龙．基于自然正交展开的神经网络长期预报模型[J]．自然灾害学报，2003，12(2)．127-132．
[68] 张承福．人工神经网络在天气预报中的应用[J]．气象，1994，20(6)，43-47．
[69] 姜天戟，袁曾任．新激活函数下前馈型神经网络及其在天气预报中的应用[J]．信息与控制，1995，24(1)：47-51．
[70] Tony Hall. Precipitation Forecasting Using a Neural Network[J], Weather and Forecasting. 1999, 14(3): 338-345.
[71] Tim Bellerby, Martin Todd, Dom Kniveton. Chris Kidd, Rainfall Estimation from a Combination of TRMM Precipitation Radar and GEOS Multispectral Satellite Imagery through the Use of an Artificial Neural Network[J]. Journal of Applied Meteorology, 2000, 39 (12): 2115-2128.
[72] Hongping Liu, V. Chandrasekar, and Gang Xu. An adaptive Neural Network Schema for Radar Rainfall Estimation from Wsr-88d Observations[J]. Journal of Applied Meteorology, 2001, 40(11): 2038-2050.
[73] 师春香，卢乃锰，张文建．卫星面雨量估计人工神经网络方法[J]．气候与环境研究．2001，6(4)：467-472．
[74] 熊秋芬，胡江林，展军．神经网络方法在静业卫星多通道资料估算降水中的应用[J]．气象，2002．28(9)：17-21．
[75] 胡江林，涂松柏，冯光柳．基于人工神经网络的暴雨预报方法探讨[J]．热带气象学报，2003，19(4)：422-428．
[76] Auroop R. Ganguly, Rafael L. Bras, Distributed Quantitative Precipitation Forecasting Using Information from Radar and Numerical Weather Prediction Models[J]. Journal of Hydrometeorology, 2003, 4(6):1168-1180.
[77] Roderick A. Scofield, Robert J. Kuligowski. Status and Outlook of Operational Satellite Precipitation Algorithms for Extreme-Precipitation Events[J]. Weather and Forecasting, 2003, 18(6):1037-1051.
[78] T. J. Bellerby. A Feature-Based Approach to Satellite Precipitation Monitoring Using Geostationary IR Imagery[J]. Journal of Hydrometeorology, 2004, 5(5): 910-921.
[79] 桂海林，郁凡．用神经网络进行多波段卫星信息的降水估测[J]．气象科学，2004，24(2)：177-184．
[80] Francisco J. Tapiador, Chris Kidd, Vincenzo Levizzani, and Frank S. Marzano. A Neural Networks-Based Fusion Technique to Estimate Half-Hourly Rainfall Estimates at 0.1° Resolution from Satellite Passive Microwave and Infrared Data[J]. Journal of Applied Meteorology, 2004, 43(4): 576-594.
[81] 段婧，苗春生．人工神经网络在梅雨期短期降水分级预报中的应用[J]．气象，2005，31(8)：31-36．
[82] 胡波，杜惠良，滕卫平，肖云．用红外云图估算热带气旋短时雨量[J]．气象，2006，32(1)：74-77．
[83] 林健玲．金龙，彭海燕．区域降水数值预报产品人工神经网络释用预报研究[J]．气象科技．2006，34(1)：12-17．
[84] 林健玲，金龙，林开平．神经网络方法在广西日降水预报中的应用[J]．南京气象学院学报，2006，29(2)：215-219．
[85] Arnold F Shapiro. The merging of neural net-works, fuzzy logic and genetic algorithms[J]. Insurance: Mathematics and Economics, 2002, 31:115-13t.
[86] Blanco A, Delgado M, Pegalajar M C. A real-coded genetic algorithm for training recurrent neural networks[J]. Neural Networks, 2001, 14: 93-105.
[87] V. Lakshmanan. Speeding Up a Large-Scale Filter[J]. Journal of Atmospheric and Oceanic Technology, 2000, 17(4): 468-473.
[88] Henry K. Ntale, Thian Yew Gan, and Davison Mwale. Prediction of East African Seasonal Rainfall Using Simplex Canonical Correlation Analysis[J]. Journal of Climate, 2003, 16(12): 2105-2112.
[89] 王秀春，智会强．人工神经网络和遗传算法在导热反问题中的应用[J]．河北工业大学学报，2004，33(2)：171-176．
[90] 陈海英，郭巧，徐力．基于混合遗传神经网络的百米跑成绩预测方法[J]．计算机仿真，2004，21(2)：89-92．
[91] 谢冰，戴盛，谢科范．基于遗传神经网络的工业股票指数预测[J]．湖南大学学报，2004，18(6)：59-64．
[92] 陈守煜，王大刚．基于遗传算法的模糊优选BP网络模型及其应用[J]．水利学报，2003，(5)：116-121．
[93] 罗长寿，左强，李宝国．基于遗传算法的人工神经网络模型在冬小麦根系分布预报中的应用[J]．应用生态学报，2004，15(2)：354-356．
[94] 郭章林，刘明广，解德才．震灾经济损失的神经网络模型[J]．自然灾害学报，2004，13(6)：92-96．
[95] 李爱云，吴建华，曹广学．遗传算法与神经网络在洪水预报中的应用[J]．太原理工大学学报，2005，36(5)：585-588．
[96] 李鸿雁，侯光明．提高洪水智能预报中洪峰预报精度方法的研究[J]．自然灾害学报，2004，13(4)：128-134．
[97] 林建宇．BP神经网络结合遗传算法进行股市预测的研究[J]．福建电脑，2005，(12)：91-92．
[98] 刘明广，郭章林．基于GA-ANN的震灾风险预测模型研究[J]．中国工程科学，2006，8(3)：83-86．
[99] 吴建生．旱涝灾害的遗传-神经网络集成预测方法研究[J]．广西科学，2006，13(3)：203-206．
[100] 洪梅，张韧，吴国雄，何金海，余丹丹．副热带高压强度变化的模糊聚类诊断预测[J]．应用气象学报，2006，17(4)：459-466．
[101] Miller GF, Todd PM and Hedge SU. Designing neural networks using genetic algorithm[C]. Proc. Of 3rd conf. On Arlington, 1989, 479-384.
[102] Harp SA, Samad T. Optimizing neural networks with genetic algorithms[C]. Proceedings of the American Power Conference, 1991, (11): 38-43.
[103] Goldberg D E. Genetic Algorithms in Search, Optimization, and Machine Learning[J]. Reading, MA, Addision Wisely, 1989.
[104] Back T. Schwefel H-P. An overview of evolutionary algorithms for parameter optimization[J]. Evolutionary Computation. 1993, (1): 1-23.
[105] Maniezzo V, Genetic evolution of the topology and weight distribution of neural networks[J]. IEEE, Trans. Neural Networks, 1994, (1): 39-53.
[106] 周娜，周燕屏．神经网络及遗传算法在径流预报中的应用[J]．计算机仿真，2004，21(9)：117-119．
[107] 李爱云，吴建华．神经网络在径流水量还原计算中的应用[J]．东北水利水电，2006，24(1)：9-11．
[108] 金龙，吴建生，林开平，陈冰廉．基于遗传算法的神经网络短期气候预测模型[J]．高原气象，2005，24(6)：981-987．
[109] 谷晓平，王长耀，袁淑杰．GA-BP神经网络模型在流域面雨量预报的应用研究[J]．热带气象学报，2006，22(3)：248-252．
[110] Baum E B, Hausster D. What size net gives valid generalization[J]. Neural Computation, 1989, (1): 151-160.
[111] Moody, J.E.. The effective number of parameters: An analysis of generalization and regularization in nonlinear learning system[J]. Adv. Neural Inf. Process. Syst. 1992, 4:848-854.
[112] Barron A R. Approximation and estimation bounds for artificial neural networks [J]. Machine Learning, 1994, (14): 115-133.
[113] Cataltepe Z Abu-mostafa Y.S, Magdon-lsmail M No free lunch for earlystopping[J]. Neural Computation, 1999, 11: 995-100.
[114] Amari S, Muller K R, Asymptotic statistical theory of overtraining and cross-validation[J]. IEEE Transactions on Neural Networks, 1997, 8(5): 985-996.
[115] 胡耀垓，李凯扬，钟毓宁．一种改进的神经网络BP算法[J]．武汉大学学报(自然科学版)．1999，45(1)：25-29．
[116] 林俊，章兢．B-P网络泛化性能的改善[J]．计算机与现代化，2001，73(3)：1-5．
[117] 李俭川，秦国军，温熙森．神经网络学习算法的过拟合问题及解决方法[J]．振动、测试与诊断，2002，22(4)：260-264．
[118] 武妍，张立明．神经网络的泛化能力与结构优化算法研究[J]．计算机应用研究，2002，19(6)：21-25．
[119] 李祚泳．彭荔红．BP网络学习能力与泛化能力满足的不确定关系式[J]．中国科学：E辑 2003，33(10)：887-895．
[120] 殷春霞，胡雪松，郭元裕等．改善径向基函数网络泛化性能的主成分分析方法及应用研究[J]．武汉水利电力大学学报，2000，33(2)：85-89．
[121] 江学军，唐焕文．前馈网络泛化性能力的系统分析[J]．系统工程理论与实践，2000，20(8)：36-40．
[122] 杨晓红，刘乐善．用遗传算法优化神经网络结构[J]．计算机应用与软件，1997，14(3)：59-65．
[1] 朱翚．芮延年．严红．基于人工模糊神经网络高速造纸机多机同步智能控制[J]．电机一体化，2006，12(1)：60-62．
[2] 秦宏伍，庄乾章．神经网络专家系统协同式智能控制系统结构[J]．长春大学学报，2004，14(6)：14-16．
[3] 沈国江，王智，刘翔，孙优贤．城市区域交通智能控制研究[J]．信息与控制，2004，14(6)：14-16．
[4] 蒋天发，王江晴．神经网络PID复合智能控制参数自整定研究[J]．武汉大学学报(工学版)，2003，36(4)：111-114．
[5] Pappis C P, Mamdani E H. A fuzzy logic controller for atraffic junction[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1997, 7(10):707-717.
[6] Lee J H, Lee K M, Leekwang H. Traffic control of intersection group based on Fuzzy logic[C]. Proceedings of the 6th International Congress on Fuzzy System, 1995: 465-468.
[7] Paoram De., Amodified Smith. Oredictor and controller for unstable processes with delay[J], control, 1995, 41(4): 1025-1036.
[8] Straub S, Schroder D. Identification of nonlinear dynamic systems with recurrent neural networks and Kalman filter methods[C]. IEEE ISCAS' 96. 1996, 3: 341-344.
[9] Korbicz J, Janczk A. A neural network approach to identification of structural systems[C]. IEEE ISLE'96, 1996,1: 98-103.
[10] 文卉．王创新．基于神经网络算法的频谱分析[J]．湖南师范大学自然科学学报，2006，29(1)：47-51．
[11] 谭德荣．韩加蓬．基于BP的车辆系统故障诊断模式识别[J]．山东理工大学学报，2003，17(3)：8-12．
[12] HO T K, Hull J J, Srihari S N. Decision combination in multiple classifier system[J]. IEEE Trans on PAMI, 1994, 16(1):66-75.
[13] Grossberg S. Nonlinear Neural Networks: Principles, Mechanisms and Architectures[J]. Neural Networks, 1998, 1(1): 47-61.
[14] 黄雪梅．唐治德，赵一凡，舒志强．BP网络研究及其在肺癌诊断系统中的应用[J]．重庆大学学报(自然科学版)，2005，28(1)：42-44．
[15] Falchini M, Stecco A, Carmicnani L. Neural Network Based Detection of Pulmonary Nodules on Chest Radiographs[J]. Radio Med, 1999, 98(4): 259-263.
[16] Nakamura K, Yoshida H, Engelmann R. Computerized Analysis of the Likelihood of Malignancy in Solitary Pulmonary Nodules with Used of Artificial Neural Networks[J]. Radiology, 2000, 214(3): 823-830.
[17] 蒋宗礼．人工神经网络导论[M]．北京：高等教育出版社．2001．
[18] Martin T．Hagan，Howard B．Demuth．Mark H．Beale著．戴葵等译．神经网络设计[M]．北京：机械工业出版社，2002．
[19] Simon Haykin著，叶世伟，史忠植译．神经网络原理[M]．北京：机械工业出版社，2004．
[20] Hecht-Nielsen R. Application of counter-propagat ion network[J]. Neural Network, 1988, 1(2): 131-140.
[21] 徐丽娜．神经网络控制[M]．哈尔滨：哈尔滨工业大学出版社，2003．
[22] 王旭，王宏等．人工神经网络原理与应用[M]．沈阳：东北大学出版社，2000．
[23] 闻新，周露等，Matlab神经网络仿真与应用[M]．北京：科学技术出版社，2003．
[24] 高隽．人工神经网络原理及仿真实例[M]．北京：机械工业出版社，2003．
[25] 从爽．面向Matlab工具箱的神经网络理论与应用[M]．合肥：中国科学技术大学出版社，1998．
[26] 周继成等．人工神经网络—第六代计算机的实现[M]．北京：科学普及出版社，1993．
[27] 周继成．人工神经网络进展(Ⅰ)[J]．应用声学，1991，10(5)：39-46．
[28] 周继成．人工神经网络进展(Ⅱ)[J]．应用声学，1991，10(6)：39-42．
[29] Hebb D O. The Organization of Behavior[M]. New York: Wiley, 1949.
[30] F. Rosenblatt. Storage and Organization in the brain[J]. Psychological Review, 1958, 65(6): 386-392.
[31] 周抚生，李春龙．人工神经网络简介及在油田土建工程中的应用展望[J]．油气田地面工程，1999，18(1)：63-67．
[32] Derek F., stubbs M. D. Neurocomputer[M]. Published with permission of springer-verlag international publications june, 1989.
[33] Frank Rosenblatt. Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms[M]. Spartan Books, Washington, DC, 1962.
[34] Grossberg, S. Nonlinear difference-differential equations in prediction and learning theory[J]. Proceedings of the National Academy of Sciences, 1967, 58: 1329-1334.
[35] Marvin Minsky. Seymour Papert. Perceptrons[M], The MiT Press, Expand edition, 1969.
[36] Grossberg, S.. Some physiological and biochemical consequences of psychological postulates[J], Proceedings of the National Academy of Sciences, 1968, 60: 758-765.
[37]Grossberg, S. . Some networks that can learn, remember, and reproduce any number of complicated space-time patterns[J]. Journal of Mathematics and Mechanics, 1969, 19: 53-91.
[38]Grossberg, S. . On learning of spatiotemporal patterns by networks with ordered sensory and motor components[J]. Excitatory components of the cerebellum. Studies in Applied Mathematics, 1969, 48: 105-132.
[39]Kohonen, T. Self-Organization and associated memory [M]. Berlin: Springer-Verlag, 2nd Edition, 1987:1-65.
[40]Teuvo Kohonen, Panu Somervuo. Self-organizing maps of symbol strings[J]. Neurocomputing, 1998, 21:19-30.
[41] J. J. Hopfield, F. A. Ferrone. Rate of quarternary structure change in hemoglobin measured by modulated excitation[J]. PNAS 73, 1976: 4497.
[42]J.J. Hopfield Electron Transfer Between Biological Molecules by Thermally Activated Tunneling [J]. PNAS 71, 1974: 3640-3644.
[43]Anderson J A., Silverstein J W, Ritz S A, et al. Distinctive features, categorical perception and probability learning: Some applications of a neural model in Neurocomputing: Foundations of Research, Anderson J A and Rosenfeld E.Eds. Cambridge, M A: MIT Press, 1988: Ch. 2-Ch. 4.
[44]Golden R M. The Brain-State-in-a-Box neural model is a gradient descent algorithm[J]. Journal of Mathematical Psychology, 1986, 30(1): 73-80.
[45]Greeberg H J. Equilibria of the Brain-in-a-Box (BSB) neural model [J]. lEEE Trans on Neural Networks, 1988, 1(4): 323-324.
[46]Rumelhart D E, Williams R J. Learning representations by back-propagation errors[J]. NATURE, 1986, 323: 533-536.
[47]JohnJ. Hopfield. Neural networks and physical systems with emergent collective computational abilities[J]. PNAS 79, 1982, 2554.
[48]Hopfield J J. Neurons with Graded Respone have Collective Computational Properties Like those of Twostate Neurons [J]. Proc, Natl, Acd. Sci, 1984, 81: 3088-3092.
[49]Hopfield J J, Tank D W. Computing with Neural Circuits: A Model [J]. Science, 1986, 233: 625-633.
[50]Rumelhart D E. , Hinton G. E. , Williams R.J.. Learning Internal Representations by Error Back Propagation, in D. E. Rumelhart and L. L. McClelland (eds. ) , parallel Distributed Processing: Explorations in the Microstructure of Cognition Vol, 1, Foundations, The MIT Press, Ch8, 1986.
[51] Simon Haykin著，叶世伟，史忠植译．神经网络原理[M]．北京：机械工业出版社．2004．
[52] 金龙．神经网络气象预报建模理论方法与应用[M]．北京：气象出版社，2004．
[53] 党建武．神经网络技术及应用[M]．北京：中国铁道出版社．2000．
[54] 徐丽娜．神经网络控制[M]．北京：电子工业出版社．2003．
[55] 焦李成．神经网络系统理论[M]．西安：西安电子科技大学出版社，1990．
[56] 胡守仁，沈清，胡德文等．神经网络应用技术[M]．长沙：国防科技大学出版社，1993
[57] Kurt Hornik. Approximation capabilities of multilayer feedforward networks[J]. Nueral Networks, 1991, 4(2): 251-257.
[58] 尚钢，钟珞，陈立耀．神经网络结构与训练参数选取．[J]．武汉工业大学学报，1997，19(2)：108-110．
[1] Holland J H. Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence[M]. 1st edition, Ann Arbor, MI: The University of Michigan Press, 1975.
[2] Holland J H., Reitman J.S.. Cognitive systems based on adaptive algorithms, Pattern-directed Inference System[M]. NY: Academic Press, 1978.
[3] Goldberg DE., Genetic algorithms in search, optimization, and machine learning[M]. Reading, MA: Addison-Wesley, 1989.
[4] Goldberg DE., Deb K. A comparative analysis of selection schemes used in genetic algorithms[A]. Rawlins G. Foundations of genetic algorithms[C]. San Mateo, CA: Morgan Kaufmann, 1991.
[5] Goldberg DE, Korb B., Deb K.. Messy genetic algorithms: motivation, analysis, and 3rst results[J]. Complex Systems, 1989, (3): 493-530.
[6] 周明，孙树栋．遗传算法原理及其应用[M]．北京：国防工业出版社，1999：35-47．
[7] 张文修．梁怡．遗传算法的数学基础[M]．西安：西安交通大学出版社，2003．
[8] 胡兰萍，黄海斌．遗传算法及其在化学领域中的应用[J]．海南师范学院学报(自然科学版)，2006，19(3)：261-266．
[9] 祝江汉，李曦，毛赤龙，张利宁．多卫星区域观测任务的侧摆方案优化方法研究[J]．武汉大学学报(信息科学版)，2006，31(10)：868-870．
[10] 毛斌，张齐凯，卢海林．基于遗传算法的江汉平原CFG桩复合地基优化设计研究[J]．长江大学学报(理工卷)，2006，3(13)：97-99．
[11] 周湶，孙才新，张晓星等．基于多种群免疫遗传算法的配电网网架规划[J]．重庆大学学报(自然科学版)，2005，28(4)：36-41．
[12] 钟胜，王朝金，闻英友等．遗传算法在CDMA网络基站分布规划中的应用[J]．邮电设计，2004，(6)：9-13．
[13] Wang Jian, Zhou Jiangqi, Lin Zhongqin. Locators Optimization for Measuring Fixture Design[J]. Chinese Journal of Mechanical Engineering, 2004, 17(3):332-335.
[14] 马小明，曹云等．基于随机优化方法的大气污染物总量控制模型[J]．中国环境科学，2001，21(5)：436-439．
[15] 陈国良，王熙法．遗传算法及其应用[M]．北京：人民邮电出版社，1996．
[16] 王小平．曹立明．遗传算法—理论应用与软件实现[M]．西安：西安交通大学出版社，2002：15-17．
[17] Goldberg D. F, Real Coded Genetic Algorithm, Virtual Alphabcts and Blocking. Complex Systems, 1991 (5): 139-167.
[18] 余有明，刘玉树，阎光伟．遗传算法的编码理论与应用[J]．计算机工程与应用，2006，(3)：86-89．
[19] Raul T S., Julio C H, Alex A F. Extracting Comprehensible Rules from Neural Networks via Genetic Algorithm[J]. IEEE. 2000, 36: 130-139.
[20] 国嘉，王瑞敏．王家海．张忠民．基于遗传算法的神经网络学习方法[J]．计算机与数字工程，2004，32(5)：101．
[21] 李士勇．李盼池．基于实数编码和目标函数梯度的量子遗传算法[J]．哈尔滨工业大学学报，2006，38(6)：1216-1218．
[22] 徐静波．一种融合神经网络学习的遗传算法[J]．上海工程技术大学学报，2000，14(3)：173-177．
[23] 周娜，周燕屏．神经网络及遗传算法在径流预报中的应用[J]．计算机仿真，2004，21(9)：117-119．
[24] 杨献波，程建川，冯云飞．公路纵断面优化的遗传算法设计[J]．交通与计算机，2005，23(3)：16-19．
[25] Bagley J. D. The behavior of adaptation system which employ genetic and correlation algorithm[J], Dissertation abstracts international: 1967, 28(12).
[26] De Jong K A. An analysis of the behavour of aclassof genetic adaptive systems [D]. University of Michigan, 1975: 76-9381.
[27] Goldberg D E. Genetic Algorithms in Search, Optimization, and Machine Learning[J]. Reading, MA, Addision Wisely, 1989.
[28] Davis, L. D. Handbook of genetic algorithms[M], Van Nostrand Reinhold, 1991.
[29] Koza, J. R. Genetic programming1 [M]. Cambridge, MA: the MI Press, 1992.
[30] Michalewicz Z. Genetic Algorithms+Data Structures=Evolut on Programs[M]. Springer-Verlag, Second, Extended Edition, 1994.
[31] Hofbauer J, Sigmud K. The Theory of Evolution and Dynamical Systems[M]. Cambrige University Press, 1989.
[32] John. J. Hopfield, Dawei Dong.. Dynamic properties of neural networks with learning and feedback[J]. Network, 1992, (3):267-283.
[33] 李通化 张众杰．用数值遗传算法计算配合物的稳定常数[J]．高等学校化学学报，1995，16(3)：354-358．
[34] Lucasius C B, Beckers M L M, Kateman G. Genetic algorithms in wavelength s election: a comparative study[J]. Analytica Chimica Acta, 1994, 286: 135-153.
[35] D. Wienke, C. B. Lucasius and G. Kateman. Multicriteria target vector optimization of analytical procedures using a genetic algorithm. Part Ⅰ. Theory, numerical simulation and application to atomic emission spectroscopy[J], Analytica Chimica Acta, 1992, 265: 211-225,
[36] D. Wienke, C. B. Lucasius and G. Kateman, Multicriteria target vector optimization of analytical procedures using a genetic algorithm. Part Ⅱ. Polyoptimization of the photometric calibration graph of dry glucose sensors for quantitative clinical analysis[J], Analytica Chimica Acta, 1993, 271: 253-268.
[37] Cieniawski S E, Eheart J W, Ranjithan S. Using genetic algorithms to solve a multiobjective groundwater monitoring problem[J]. Water Resour Res, 1995, 31(2):399-409.
[38] Melanie Mitchell. An introduction to genetic algorithms[M]. Cambridge, MA: The MIT Press, 1996.
[39] Kadaba, N., Nygard, K.E.,and Juell, P. J.,Integration of adaptive machine learning and knowledgecased systems for routing and scheduling applications[J]. Expert Systems with Application, 1991, 2(1):15-27.
[40] Lin, S. H., Goodman, E. D., and Paunch, W. F., Investigating Parallel Genetic Algorithms on Job Shop Scheduling Problem[C]. In the Sixth International Conference on Evolutionary Programming, Angeline, P., Reynolds, R. J. M., and Eberhart, R. (ed.), Berlin: Springer-Verlag, 1997: 383-393.
[41] Cartwright H M, Long R A. Sumultaneous optimization of chemical flowshop sequencing and topology using genetic algorithms[J]. Ind Eng Chem Res, 1993,
32:2706-2713.
[42]Syswerda G. Study of reproduction in generational and steadystate genetic algorithms[J]. San Mateo, CA: Morgan Kaufmann. 1991: 94-101.
[43]Hilliard M R, Liepins G E. Mark Palmer, and Michael Morrow. Greedy genetics. Proc. of the 2nd Int'l. Confi. On Genetic Algorithms, 1987: 28-31.
[44]Gabbert P S. A system for learning routes and schedules with genetic algorithms[C]. In:ICGA' 91,1991: 430-436.
[45]Dechaine MD, Feltus MA. Nuclear Fuel Management Optimization Using Genetic Algorithms[J]. Nucl. Tech, 1995, 111:109-114.
[46]Lin J, Bartal Y, Uhrig R E. Predicting the severity of NPP transients using nearest neighbors modeling optimized by genetic algorithms on a parallel computer [J]. Nucl Techol, 1995, 111:46-61.
[47] Cox CS, French IG, Ho CK Improved Ml MO System-Identification and Control Using Genetic Algorithms[J]. Chemical Engineering Research & Design, 1996, 74(1) : 97-105.
[48] 邓勃,刘嘉.遗传算法在分析化学中的应用[J].分析科学学报. 1997, 13(2) : 160-168.
[49]V.O. de Haan and. G. G. Drijkoningen. Genetic algorithms used in model finding and fitting for neutron reflection experiments[J]. Physica B, 1994, 198: 24-26.
[50]Kaufman, L. , Rousseeuw, P. J. Finding Groups in Data: An Introduction to Cluster Analysis[M]. John Wiley & Sons, New York, USA, 1990.
[51]Lucasius CB, Dane AD, Kateman G. On k-medoid cluster ing of large data sets with the aid of a genetic, algorithm: background, feasibility and comparison[J]. Anal. Chim. Acta 1993; 282: 647-669.
[52] Lucasius CB, deWeijer A P, Buydens L M C, Kateman G. CFIT: a genetic algorithm for survival of the fitting[J], Chemom. Intell. Lab. Syst. , 1993, (19) : 337-341.
[53]Lucasius, C. B. and Kateman, G. Gates towards Evolutionary Large-Scale Optimisation: A Software-Oriented Approach to Genetic Algorithms [J]. Computers and Chemistry 1994, 18, 137-156.
[54]Maclay, D. , and Dorey, R. Applying genetic search techniques to drivetrain modeling[J]. IEEE Control Systems, Special Issue on Intelligent Control, 1993, 13(3): 50-55.
[55] Freeman, L. M., et al. Turning fuzzy logic controller using geneticalgorithms aerospace applications[C]. In Proceedings of the AAAIC'90 Conference, Dayton, Oct., 1990:351-358.
[56] McCallum, R. A.,and Spackman, K. A. Using genetic algorithm to learn disjunctive rules form examples[C]. In Proceeding of the International Conference on Machine Learning, San Mateo, CA: Morgan Kaufmann, 1990: 149-152.
[57] TERJEB, JON A G. Natural language analysis for semantic documant modeling[J]. Data &Knowledge engineering, 2005, 38(1): 45-62.
[58] THOMSON W T. On-line MCSA to diagnose shorted turns in low voltage stator windings of 3-phase induction motors prior to failure[A]. International Conference for IEEE IEMDC01[C]. Atlanta, USA, 2005.
[59] Bennett, K., A genetic algorithm for database query optimization[C]. IEEE conference on Evolutionary Computation, 1994: 400-407.
[60] KOCKA T, CASTELOR. Improved learning of Bayesian network[A]. Breese j, Koller D. Uncertainty in Artificial Intelligence: Proceedings of the Seventeenth Conference (UAI'2001) [C]. San Francisco, US: M Kaufmann, 2001, 269-276.
[61] Xin Yao. A review of evolutionary artifical neural network[J]. International Journal of Intelligent Systems, 1993, 8(3): 539-565.
[62] Montana, D.J.,and Davis, L..Training feed-forward neutral networks using genetic algorithms [C]. In Proceeding of the International Joint Conference on Artificial Intelligence, Los Altos, CA: Morgan Kaufmann Publishers, 1989: 762-767.
[63] 张材，谭建平．基于遗传算法-反向传播模型的板形模式识别[J]．中南大学学报(自然科学版)．2006，37(2)：294-299．
[64] Tai J C, Tseng S T, et al. Real-Time Image Tracking for Automatic Traffic Monitoring and Enforcement Applications[J]. Image and Vision Computing, 2004, 22[6]:485-501.
[65] Pal N R, Bezdek J C. On cluster validity for the fuzzy C-means[J]. IEEE Transactions on Fuzzy System, 1995,3(3): 370-379.
[66] Bala, J., De Jong, K.A., Haung, J., Vafaie, H., and Wechsler, H. Hybrid learning using genetic algorithm and decision trees for pattern classification[J]. In Proceedings of the 14th International Joint Conference on Artificial Intelligence, August 19-25, 1995, Montreal, Canada.
[67] 宋立新．王玉华，李玲远．基于遗传算法和神经网络优化的故障诊断专家系统[J]．华中师范大学学报(自然科学版)，2005，39(3)：332-335．
[68] Abdelhadi B, Benoudjit A, Naitsaid. N. Application of genetic algorithm with a novel adaptive scheme for the identification of induction machine parameters[J]. IEEE Transaction on Energy Conversion, 2005, 20(6): 284-291.
[69] Nikolopoulos, C., and Fellrath, P., et al. Hybrid expert system for investment advising[J]. Expert System, 1994, 11(4): 245-248.
[70] 李敏强．寇纪凇等．遗传算法的基本理论与应用[M]．北京：科学出版社，2002．
[71] Goldberg, D. E., Segrest, P. Finite Markov Chain Analysis of Genetic Algorithms[C]. Proc. Of Second International Conference on Genetic Algorithms. 1987: 1-8.
[72] Eiben, A. E., Aarts, E. H., and Van Hee, K. M., Global Convergence of Genetic Algorithms; An Infinite Markov Chain Analysis. Parallel Problem Solving from Nature[M]. Berlin: Spring-Verlag, 1991: 4-12.
[73] Rudolph, G.. Convergence Properties of Canonical Genetic Algorithms[J]. IEEE Trans. On Neural Networks. 1994, 5(1): 96-101.
[74] Qi X., Palmieri F. Theoretical Analysis of Evolutionary Algorithms with an Infinite Population Size in Continuous Space, Part Ⅰ: Basic Properties of selection and Mutation[J]. IEEE Trans. On Neural Network, 1994: 102-119.
[75] 恽为民，席裕庚．遗传算法的全局收敛性和计算效率分析[J]．控制理论与应用，1996，13(4)：455-460．
[76] 刘淳安．解非线性规划的多目标遗传算法及其收敛性[J]．计算机工程与应用，2006，42(25)：27-29．
[77] 罗小平，韦巍．关于生物免疫遗传算法收敛性的一般讨论研究[J]．浙江大学学报，2005，39(12)：2006-2011．
[78] 刘淳安．多目标遗传算法的收敛性研究[J]．西华大学学报(自然科学版)，2005，24(6)：22-25．
[79] 丁建立，陈增强，袁著祉．遗传算法与蚂蚁算法融合的马尔可夫收敛性分析[J]．自动化学报，2004，30(4)：629-634．
[80] 吴建生，农吉夫，金龙，李日光。遗传算法收敛性分析[J]，广西师范学院学报(自然科学版)，2004，21(1)：48-52．
[81] De Jong K A. Genetic algorithms: a 25 years perspective. Computational intelligence imitating life[B]. New Yourk: IEEE press 1994:125-136.
[1] 金龙，况雪源，黄海洪，覃志年．人工神经网络预报模型的过拟合研究[J]．气象学报，2004，62(1)：62-70．
[2] Wu Yan, Zhang Liming. A new regularization learning method for improving generalization capability of neural network[C], proceedings of 4th world congress on intelligent control and automation, Shanghai,2002, #: 2011-2015.
[3] Saito K, Nakano R. Second-order learning algorithm with squared penalty term[J]. Neural Computation, 2000,12(3):709-729.
[4] 魏海坤，徐嗣鑫，宋文忠．神经网络的泛化理论和泛化方法[J]，自动化学报，2001，27(6)：806-815．
[5] Baum E B, Haussler D, What Size Net Gives Valid Generalization?[J]. NIPS 1,1989, San Mateo, CA, 81-90.
[6] Turmon M J, Fine T L. Sample Size Requirement for Feedforward Neural Networks Classifiers[C]. In: IEEE 1993 Intern, Sympos. Inform. Theory, 432-438.
[7] Mass W. Neural nets with superlinear VC-dimension[J]. Neural Computation. 1994, (6): 877-884.
[8] VapmkV, Levin E, Lecun Y. Measuring the VC-dimension of learning machine[J], Neural Computation. 1994, (6):851-876.
[9]. Niyogo P, Girosi F. On the relationship between generalization error, hypothesis complexity, and sample complexity for radial has s function[J]. Neural Computation. 1996, (8):819-842.
[10] Girosi F., Jones M, Poggio T. Regularization theory and neural networks architecture[J]. Neural Computation. 1995, (7):219-269.
[11] 董聪，郭晓华．计算智能中若干热点问题的研究与进展[J]．控制理论与应用．2000，17(5)：691-698．
[12] Homik K. Approximation capabilities of multilayer feedforward networks[J]. Neural Netwoks, 1991, (4):551-557.
[13] 董聪，郦正能，夏人伟，何庆芝．多层前向网络研究进展及若干问题[J]．力学进展．1995，25(2)：186-196．
[14] 江学军，唐焕文．前馈神经网络泛化能力的系统分析[J]．系统工程理论与实践，2000 (8)：36-40．
[15] R Reed.Pruning Algorithms-A survey[J].IEEE Trans.Neural Networks,1993. (4):740-747.
[16] 张乃尧，阎平凡．神经网络与模糊控制[M]．北京，请华大学出版社，1998．
[17] Willam Finnoff, Ferdinand Hergert, Hans Georg Zimmermann. Improving Model Selection by Nonconvergent Methods[J]. Neural Networks, 1999,12(1):79-89.
[18] L Holmotrom, P Koistinen.. Using Additive Noise in Back- propagation Training[J]. IEEE Trains. Neural Networks, 1992,3(1):24-38.
[19] Moody J E. The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning System[J]. NIPS 4. 1992, San Mateo, CA:847-854.
[20] Barron A R. Approximation and estimation bounds for artificial neural networks[J]. Machine Learning, 1994, (14):115-133.
[21] Partridge D. Network generalization differences quantified[J]. Neural Networks. 1996,9(2): 263-271.
[22] 袁美英，周秀杰，陈威．人工神经网络在温度和降水预报中的应用[J]．黑龙江气象，2000(3)：17-19．
[23]．冯光柳，崔春光．三峡地区降水神经元方法预报系统[J]．气象，2000，26(8)：25-26．
[24] 熊秋芬，胡江林．神经网络方法在静止卫星多通道资料估算降水中的应用[J]，气象，2002，28(9)：17-21．
[25] Abu-mostafa Y S. A Method of Learning From Hints[J]. NIPS 5, 1993, San Mateo, CA: 73-80.
[26] Mackay D J C, Bayesian interpolation[J]. Neural Computation, 1992,(3):415-447.
[27]. Williams P M, Bayesian regularization and pruning using a laplace prior[J]. Neural Computation, 1995, (7):117-143.
[28]. Abu-Mostafa Y S. Hints and the VC-dimension[J]. Neural Computation, 1993, (5):415-447.
[29] Kolen J F., Pollack J B. Back Propagation is Sensitive to Initial Conditions[J] NIPS 3, 1991, San Mateo, CA:860-867.
[30] Schmudt W F, Raudys S, Kraaijveld M A et al. Initialization Back-propagation and generalization of feed-forward classifiers[J]. InProc. IEEE Int. Conf. Neural Networks, 1993, 598-604.
[31] Atiya A, Ji C Y. How initial conditions affect generalization performance in large networks [J]. IEEE Trans Neural Networks, 1997, 8(2):448～451.
[32] 董聪．人工神经网络：当前的进展与问题[J]．科技导报，1999，7：26-30．
[33] Reed R. Pruning algorithms: A survey[J]. IEEE Trans, Neural Networks, 1993, (4):740-747.
[34] Wang C, Venkatesh S. Optimal Stopping and Effective Machine Complexity in Learning[J]. NIPS 6.1994, San Mateo, CA:263-270.
[35] Tom M．Mitchell著．机器学习[M]．曾华军，张银奎等译．北京：机械工业出版社．2003．
[36] Levin E, N Tishby, S A Solia. A statistical approach to learning and generalization in layered neural networks[C]. Proc IEEE, 1990, 78(10):1568-1574.
[37] 董聪，刘西拉．广义BP算法及网络容错和泛化能力的研究[J]．控制与决策，1998，13(3)：120-124．
[1] 任宏利，高丽，张培群等，相空间中划分大尺度异常雨型的初步研究[J]．气象学报，2004，62(4)，459-467．
[2] Jin Long, Luo Ying, Guo Guang, et al. Study on mixed model of neural network for farmland flood/drought prediction[J], ActaMeteorological Sinica, 1997,11(3): 364-373.
[3] Tony Hall. Precipitation forecasting using a neural network[J]. Weather and Forecasting, 14(3): 338-345.
[4] Marzban C, Witt Arthur, Thiria S, et al. A Bayesian neural network for sever hail size prediction[J]. Weather and Forecasting, 2000,16(5): 600-610.
[5] Silverman D, Dracup J. Artificial network and long-rang Precipitation in California[J]. Journal of Applied Meteorology, 2000,31(1): 57-66.
[6] Jin Long, Qing Weiliang. Study on combination of ANN method with mean generation function for short-term climate prediction[C]. 8th International Conference on Neural Information Processing, Shanghai, China, Fudan University Press, 2001,2:981-985.
[7] din Long, du Weimin, Miao Qilong. Study on Ann-based multi-step prediction model of short-term climatic variation[J]. Advances in Atmospheric Sciences, 2000, 17(1):157-164.
[8] 段婧，苗春生．人工神经网络在梅雨期短期降水分级预报中的应用[J]，气象，2005，31(8)：31-36．
[9] 桂海林，郁凡．用神经网络进行多波段卫星信息的降水估测[J]，气象科学，2004，24(2)，177-184．
[10] 艾艳，汤志亚，王敏．基于8P神经网络的短期降水预报[J]．河南教育学院学报(自然科学版)，2004，13(3)：60-62．
[11] 李才媛，王仁乔，王丽等．长江上游流域短期强降水面雨量预报系统[J]，气象，2003，29(3)：34-37．
[12] 熊秋芬，胡江林，夏军．神经网络方法在静业卫星多通道资料估算降水中的应用[J]．气象，2002，28(9)，17-21．
[13] 牛文全，李靖．降水量的BP人工神经网络预测模型极其应用[J]．西北农林科技大学学报(自然科学版)，2001，29(4)：103-106．
[14] 师春香，卢乃锰，张文建．卫星面雨量估计人工神经网络方法[J]．气候与环境研究，2001，6(4)，467-472．
[15] 孙日丁，周官辉，杜滨鹤等．人工神经网络方法在鹤壁汛期降水预报中的应用[J]．河南气象，2004，(3)：12-13．
[16] 李伟钢，Maria，C V Ramjrez，Nelson J Ferreira，石立华，Leonardo D de A sa．气象卫星云图的多分辨小波分解及人工神经网络降水估计研究[J]，南京气象学院学报，2000，23(2)：277-282．
[17] 尚钢，钟珞，陈立耀．神经网络结构与训练参数选取[J]．武汉工业大学学报．1997，19(2)：108-110．
[18] Hechi-Nielsen, R. Theory of the back propagation neural network[C]. Int. J. Conf. On Neural Network, Washington D. C., 1989, (1): 593—605.
[19] 张立明．人工神经网络的模型及其应用[M]．上海：复旦大学出版社，1993，32-51．
[20] Kakeya H, Dkabe Y. Fast combinatorial optimization with parallel digital computers[J]. IEEE TRANSACTIONS on Neural Networks, 2000, 11(6): 1323-1331.
[21] 吕柏权，李天择．一种优化神经网络结构算法[J]．华北电力大学学报，1996，23(3)：36-40．
[22] Junichi Murata，Hiroshi Fujii，Kensuke Ikeda，Kotaro Hirasawa．A Structure Design Method for Multiayer Networks Based on Redundancy Test[C]．计测自动制御学会论文集(日本)，1995，32(2)：236-243．
[23] 马正华，薛国新．BP神经网络训练的改进[J]．江苏理工大学学报(自然科学版)，2000，21(1)：79-82．
[24] 高洪深，陶有德．BP神经网络的改进[J]．系统工程理论与实践，1996，(1)：67-71．
[25] 徐晋．基于重置的LM变结构BP神经网络[J]．系统工程理论与实践，2004，(1)：120-125．
[26] 林正炎，陆传荣．概率极限理论基础[M]．北京：高等教育出版社，2001．27-28．
[27] 林开平，金龙，林健玲．基于遗传—神经网络的数值预报产品在短期降水预报释用方法研究[J]．气象学报，2005，63(增刊)：23-28．
[28] 金龙，况雪源，黄海洪等．人工神经网络预报模型的过拟合研究．气象学报[J]，2004， 62(1)：62-70．
[29] 祝从文，TetsuoNakazawa，李建平．大气季节内震动对印度洋-西太平洋地区热带低压／气旋生成的影响[J]．气象学报，2004，62(1)，42-50．
[30] 林开平，孙崇智，郑凤琴等．丘陵地区面雨量计算方法及应用[J]．气象，2003．29(10)：8-16．
[31] 林开平，孙崇智，陈冰廉等．广西主要江河流域的面雨量合成分析与洪涝的关系[J]．热带地理，2003，23(3)：164-170．
[32] Sim D. Aberson, Charles R. Sampson. On the Predictability of Tropical Cyclone Tracks in the Northwest Pacific Basin[J]. Monthly Weather Review. 2003, 131 (7): 1491-1497.
[33] M. Bessafi, A. Lasserre-Bigorry. Statistical Prediction of Tropical Cyclone Motion: An Analog-CLIPER Approach[J]. Weather and Forecasting. 2002, 17(4): 821-831.
[1] JIN Long, KONG Xueyuan, HUANG Haihong. Study on the Overfitting of the Artificial Neural Network Forecasting Model[J]. ACTA METEOROLOGICA SINCA, 2005, 19(2): 216-225.
[2] 魏海坤，徐嗣鑫，宋文忠．神经网络的泛化理论和泛化方法[J]，自动化学报，2001，27(6)：806-8t5．
[3] Kowalczyk A, Ferra H. Generalization in Feedforward Networks[J]. NIPS 7, 1995, Cambridge, MA: 215-222.
[4] Barron A R. Approximation and estimation bounds for artificial neural networks[J]. Machine Learning, 1994, (14): 115-133.
[5] Pertridge D. Network generalization differences quantified[J]. Neural Networks, 1996, 9(2): 263-271.
[6] Cataltepe Z, Abu-Mostafa Y S, Magdon-lsmail M. No free lunch for early-stopping[J]. Neural Computation, 1999, (11): 995-1009.
[7] 张鸿宾．训练多层网络的样本数问题[J]．自动化学报，1993，19(1)：71-77．
[8] G D Magoulas, V P Plagiananakos, M N Vrahatis. Globally convergent algorithms with local learning rates[J]. IEEE Trans on Neural Networks, 2002, 13(3): 774-779.
[9] K Eom, K Jung, H Sirisena. Performance improvement of back-propagation algorithm by automatic activation function gain tuning using fuzzy logic[J]. Neurocomputing, 2003, 50: 439-460.
[10] 冯乃勤，王芳，丘玉辉．提高神经网络泛化能力的研究[J]．计算机工程与应用．2006，(4)：38-41．
[11] 武妍，王守觉．一种通过反馈提高神经网络学习性能的新方法[J]．计算机研究与发展．2004，41(9)：1489-1492．
[12] 刘青，周鹏．基于强泛化神经网络的大规模基因表达数据分析[J]．计算机工程．2005，31(3)．189-191．
[13] Reed R. Pruning algorithms: A survey[J]. IEEE Trans. Neural Networks, 1993,(4): 740-747.
[14] Kwok T Y, Yeung D Y. Constructive algorithms for structure learning in feedforward neural networks for regressing problems[J]. IEEE Trans. Neural Networks, 1997, (8): 630-645.
[15] Maniezzo V. Genetic evolution of the topology and weight distribution of neural networks[J]. IEEE Trans. Neural Networks. 1994, (5): 39-53.
[16] Murata N, Yoshizawa S, Amari S. Networks information criterion-determining the number of hidden units for an artificial neural network model[J]. IEEE Trans, Neural Networks, 1997, 5(6): 865-872.
[17] 黄山松，杜继宏，冯元昆．前向神经网络的处理能力和推广性量度[J]．清华大学学报(自然科学版，1999，39(7)：54-58．
[18] Treadgold N K, eedeon T D. Exploring Constructive Cascade Networks[J]. IEEE Transaction on Neural Networks, 1999, 10 (6): 1335-1350.
[19] Ponnapalli PVS, Ho K C, Thomson M. AFormal Selection and Pruning Algorithm for Feedforward Artificial Neural Network Optimization[J]. IEEE Transaction on Neural Networks, 1999, 10 (4): 964-968.
[20] 刘国东，丁晶．BP网络用于水文预测的几个问题探讨[J]．水利学报，1999，(6)：1-4
[21] 张文鸽，吴泽宁，逯洪波．BP神经网络的改进及其应用[J]．河南科学，2003，21(2)：2002-2006．
[22] Holmstrom L, Koistinen P. Using additive noise in backpropagation training[J]. IEEE Trans. Neural Networks, 1992, 3(1): 24-38.
[23] George N K. On overfitting, generalization, and randomly expanded training ser[J]. IEEE Trans. Neural Networks, 2000, 11(5): 1050-1057.
[24] 杨慧中，卢鹏飞，张素贞，陶振麟．网络泛化能力与随机扩展训练集[J]．控制理论与应用．2002，19(6)：963-966．
[25] 李杰，韩正之．神经网络的学习误差函数及泛化能力[J]．控制与决策，2000，15(1)：95-97．
[26] Sietsma J, Dow R J F. Creating artificial neural networks that generalization[J]. Neural Networks, 1991, (4): 67-79.
[27] Bishop C M. Training with noise is equivalent to Tikhonov regularization[J]. Neural Computation. 1995, (7): 108-116.
[28] An G. The effect of adding noise during backpropagation training on a generalization performance[J]. Neural Computation. 1996, (8): 643-671.
[29] Sjoberg J, Ljung L. Overtraining, regularizationand searching for aminimum, with application to neural networks[J]. International Journal of Control, 1995, 62(6): 1391-1407.
[30] Cataltepe Z, Abu-Mostafa Y S, Magdon-Ismail M. No free lunch for earlystopping[J]. Neural Computation. 1999, (11): 995-1009.
[31] 武美先，张学良，温淑花，李海楠．BP神经网络及其改进[J]．太原科技大学学报，2005，26(2)：201-130．
[32] 马正华，薛国新．BP神经网络训练的改进[J]．江苏理工大学学报(自然科学版)，2000，21(1)：79-82．
[33] 董武，李树祥，沈振康．神经网络BP学习算法的改进[J]．中国医学物理学杂志，1997，14(1)：23-25．
[34] 周凤利，李绍滋，梁文林．一种改进的BP算法[J]．电器传动自动化，1997，19(2)：39-41．
[35] 朱宏平，张源．基于自适应神经网络的结构损伤检测[J]．力学学报，2003，35(1)：110-115．
[36] 宋宜斌，王培进．多层前馈神经网络改进算法及其应用[J]．计算机工程，2003，29(14)：109-111．
[37] 周龙，詹琼华．多层前馈神经网络中改进BP算法的研究[J]．武汉食品工业学院学报，1999，(1)：69-74．
[38] 庞元明，施卫东．BP神经网络震荡和平台问题的解决[J]．北京理工大学学报，1995，15(5)：72-77．
[39] 姜绍飞，张春丽，钟善桐．BP网络模型的改进方法探讨[J]．哈尔滨建筑大学学报．2000，33(5)：57-60．
[40] 陈善广，鲍勇．BP神经网络学习算法研究[J]．应用基础与工程科学学报，1995，(4)：437-442．
[41] 王铁，陈进．BP算法中学习率及形状因子对学习速度的综合影响[J]．上海交通大学学报，1997，31(3)：109-112．
[42] 吴佑寿．一种激励函数可调的新人工神经网络及应用[J]．中国科学(E辑)，1997，(1)： 55-59．
[43] 张胜，刘红星，高敦堂，王蔚．神经网络泛化特性改善方法[J]．计算机应用与软件．2005，22(12)：12-14．
[44] Gencay-R, Qi-M. Pricing and Hedging Derivative Securities with Neural Networks-Bayesian Regularization, Early Stopping and Bagging[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12(4): 726-734.
[45] Lampinen-J, Vehtari-A. Bayesian-Approach for Neural Networks-Review and Case-Studies[J], Neural Netwoks, 2001, 14(3): 257-274.
[46] Leung-CT, Chow-TWS. Least 3rd-Order Cumulant Method with Adaptive Regularization Parameter Selection for Neural Networks[J], Artificial Intelligence, 2001, 127(2): 169-197.
[47] WANG-ZO, ZHU-T. An Efficient Learning Algorithm for Improving Generalization Performance of Radial Basis Function Neural Networks[J]. Neural Networks, 2000, 13(4): 545-553.
[48] Harris Druck, Yann Le Cun. Improving Generalization Using Double Backpropagation[J]. IEEE Trans. Neural Networks, 1992, 3(6): 991-997.
[49] 付秀琢，王兆辉．基于实例改进的BP算法的联合应用[J]．山东交通学院学报，2004，12(1)：33-36．
[50] 叶东毅．基于模型逼近度和接受概率的一个变步长快速BP学习算法[J]．计算机学报，1996，(10)：738-787．
[51] 叶东毅，何萧玲．前馈神经网络的一个改进的BP学习算法[J]．福州大学学报(自然科学版)，1998，26(2)：22-26．
[52] 张茂元，卢正鼎．基于李雅普诺夫函数的BP神经网络算法的收敛性分析[J]．小型微机计算机系统，2004，25(1)：93-95．
[53] 张海燕，胡光锐，张东红．多层前向神经网络的一种改进BP算法[J]．通讯技术，2003，(11)：6-7．
[54] 裴浩东，苏宏业，褚健．多层前向神经网络的权值平衡算法[J]．电子学报，2002，30(1)：139-141．
[55] 张学良，温淑花，武美先．前向神经网络的一种快速学习算法[M／CD]．第十三届全国神经网络学术大会，2004，10．
[56]Martin R, Heinrich B. A Direct Adaptive Method for Faster Back Propagation Learning: The RPROP Algorithm[A], Ruspini H. Proceedings of the IEEE International Conference on Neural Net works(ICNN)[C]. IEEE Press, New York. 1993, 586-591.
[57]Kennedy J , Eberbart R C. Particle swarm optimization[C], Proc IEEE international conference on Neural Networks. USA:IEEE Press, 1995, (4): 1942-1948.
[58] Kaiping Lin, Long Jin, Jianling Lin, Binglian Chen. The Relationship Between the Multi-Collinearity and the Generalization Capability of the Neural Network Forecast Model [C]. Sixth World Conference on Intelligence Control and Automation, IEEE Press ,2006, 12(1):56-60.
[2] John Hopfield, Tank D W. "Neural" computation of decisions of optimization problems[J]. Biol Cybern, 1985, 52(3): 141-152.
[3] Aiko Prasn. Network management achitectures [D]. CTIT Ph.D-thesis series No. 95 (02),1995.
[4] Amari S. Natural gradiant works efficiently to learning[J], Neural Computation, 1998, NO: 252-276.
[5] Atiya A, C. Ji. How initial conditions affect generalization performance in large networks[J]. IEEE Trans on neural networks. 1997, 8(2): 448-451.
[6] Bagley J.D. The behavior of adaptation system which employ genetic and correlation algorithm[J]. Dissertation abstracts international, 1967, 28(12): 34-41.
[7] Bhattacharrya S, Pendharkar PC. Inductive evolutionary and neural techniques for discri- mination[J]. Decision Sciences, 1998, (4): 71-99.
[8] De JongK. A. An analysis of the behavior of aclassof genetic adaptation system [D]. Ph.D Dissertation, University of Michigan, 1975.
[9] Dorigo M., and Schneph U., et al. Genetic-based machine learning and behavior-based robotics: a new synthesis[J]. IEEE Transactions on Systems, Man and Cybernetics, 1993, 23(1):141-154.
[10] Foresee F D, Hagan M T. Gauss-Newton approximation to Bayesian regularization[J]. In: Proceedings of the 1997 International Join Conference on Neural Networks, Houston, Texas, 1997:1930-1935.
[11] Caren Marzban, Arthur Witt. A Bayesian Neural Network for Severe-Hail Size Prediction[J]. Weather and Forecasting, 2001,16(5), 600-610.
[12] GemanS. Neural networks and bias/variance dilemma[J]. Neural Computation, 1992, (4):1-58.
[13] HORVATH G, SZABO T. CMAC neural network with improved generalization property for system modeling[A]. Instrumentation and Measurement Technology Conference 2002[C], 2002 (2):1603-1608.
[14] 袁曾任．人工神经网络及其应用[M]．北京：清华大学出版社，1999：118-131．
[15] 温熙森，胡莺庆．丘静．模式识别与状态监控[M]．长沙：国防科技大学出版社，1997， 134-150．
[16] 李敏强．遗传算法和神经网络的结合[M]．系统工程理论与实践，1999．(2)：65-69．
[17] 方剑．席裕庚．神经网络构造设计的和方法[J]．信息与控制，1996，25(3)：156-164．
[18] 阎平凡．人工神经网络的容量、学习与计算复杂性[J]．电子学报，1995．23(1)：63-67．
[19] 秦伟良，金龙．小波网络方法用于时间序列分析中非线性模型的研究[J]．南京气象学院学报，1997，20(1)：76-80．
[20] 高建芸．基于前馈网络的热带气旋短期气候预测模型[J]．气象科学，1999，1(19)：158-164．
[21] 金龙，苗春生，陈宁等．定性和定量长期预报模型的综合分析[J]．气象学报，2000，58(4)：477-483．
[22] 金龙．罗莹．李永华．长期天气的人工神经网络混合预报模型研究[J]．系统工程学报，2003，18(4)：331-336．
[23] 金龙，朱诗武．数值预报产品的神经网络释用预报应用[C]．中国神经网络学术大会，北京：电子工业出版社，1999．
[24] 罗莹．金龙．数值预报产品完全预报(PP)方法的改进．大气科学发展战略[M]，气象出版社，2002．
[25] 李永华，刘德，金龙，基于BP神经网络的汛期降水预测模型研究[J]，气象科学，2002，22(4)：461-467．
[26] J i n Long (金龙), Luo Ying (罗莹), Guo Guang (郭光) et al. Study on mixed model of neural network for farmland Flood/Drought Prediction [J]. Acta Meteorological Sinica, 1997, 11 (3): 364-373.
[27] Jin Long (金龙), Luo Ying (罗莹), Li Yonghua (李永华). Study on Prediction Modeling of the artificial neural network from the Combination of multivariate analysis and mean generat ion funct ion [C], proceedings of the 4th World Congress on intelligent Control and automation. 2002, Shanghai, China, press of east China university of Science and technology, Vol.3, 2440-2444, IEEE Catalog Number: 02EX527C.
[28] Guo Guang (郭光), Yang Shaojin (严绍瑾), Jinlong. Time series prediction model consisting of artificial neural network and genetic algorithm[J].气象学报(英文版), 1998, 12 (2): 247-256.
[29] Jin Long (金龙), Luo Ying (罗莹). Study on flood/drought prediction neuron network method Composed of time-Series Continuation and related external variables[C]. Progress in neural information Processing, HongKong, 1996, vol.2: 732-736.
[30] Jin Long (金龙),Lou Ying (罗莹) and Lin Zhenshan (林振山). Comparison of Long-term forecasting of June-August rainfall over Changjiang-Huaihe valley[J]. Advances in Atmospheric Sciences, 1997, 14(1): 87-92.
[31] Jin Long(金龙), Qing Wei Liang(秦伟良). Study on Combination of ANN method with mean generating function for Short-term Climate prediction[C], 8th International Conference on neural information processing. Shanghai, China, Fudan university Pres, 2001, vol. 2: 981-985.
[32] 白慧卿，方宗义，吴蓉璋．基于人工神经网络的GMS云图四类云系的识别[J]．应用气象学报，1998，19(4)：402-409．
[33] 白慧卿．NWP Ⅱ+及其在方法云系分类中的应用[J]．气象．1999，25(6)：27-30．
[34] 梁益同，胡江林．NOAA卫星图像水体信息神经网络识别方法的探讨[J]．应用气象学报，2001，12(1)：85-90．
[35] 梁益同，胡江林．基于神经网络的气象卫星影像森林火点自动识别的试验研究[J]．应用气象学报．2003．14(6)：708-714．
[36] 张韧，王海俊，孙照渤等．双光谱卫星云图的模糊推理云分类[J]．防灾减灾工程学报．2004，24(3)：257-263．
[37] 王继光，张韧，王彦磊等．卫星云图样本集的FCM优化调整与云类判别[J]．防灾减灾工程学报，2005，25(2)：163-167．
[38] 王彦磊，张韧，孙照渤．基于模糊C均值聚类的云图样本修正与云类自动识别[J]．海洋科学进展，2005，23(2)：219-226．
[39] 王继光，张韧，洪梅，纪飞．卫星云图分类的一种综合优化聚类方法[J]．解放军理工大学学报(自然科学版)．2005，6(6)：585-590．
[40] 洪梅，张韧，万齐林，朱伟军．模糊聚类与遗传算法相结合的卫星云图分类[J]．地球物理学进展，2005，20(4)：1009-1014．
[41] 洪梅，张韧，孙照渤．多光谱卫星云图的高维特征聚类与降水天气判别[J]．遥感学报．2006，10(2)：184-190．
[42] Donald W. McCann. A neural network short-term forecast of Significant thunderstorms, Weather and Forecasting[J], 1992,7(3):525-534.
[43] Caren Marzban, Arthur Witt. A Bayesian Neural Network for Severe-Hail Size Prediction[J], Weather and Forecasting, 2001, 16(5): 600-610.
[44] 梅钰．人工神经网络在辐射雾预报中和应用[J]．应用气象学报．1999，10(4)：511-512．
[45] Andrew R. Dean and Brian H. Fiedler. Forecasting Warm-Season Burn-off of Low Clouds at the San Francisco International Airport Using Linear Regression and a Neural Network[J]. Journal of Applied Meteorology, 2001, 41 (6): 629-639.
[46] 金龙，申双和．罗莹等．水面蒸发计算的人工神经网络方法研究[J]．南京气象学学报，1996，19(3)，342-347．
[47] 曹杰，谢应齐．预报方程时变参数的一种新递推方案[J]．大气科学，1996，21(6)：698-704．
[48] J. Shao. Improving Nowcasts of Road Surface Temperature by a Back-propagation Neural Network[J]. Weather and Forecasting, 1998, 13(1):164-171.
[49] Lei Shi. Retrieval of Atmospheric Temperature Profiles from AMSU-A Measurement Using a Neural Network Approach[J]. Journal of Atmospheric and Oceanic Technology. 2001, 18(3): 340-347.
[50] 金龙．林熙，金健等．模块化模糊神经网络的数值预报产品释用预报研究[J]．气象学报，2003，61(1)，78-84．
[51] 周曾奎，韩贵荣，朱定真等．人工神经网络台风预报系统[J]．气象，1996，22(1)：18-21．
[52] Long-Jin Baik and Hong-sub Hwang. Tropical Cyclone Intensity Prediction Using Regression Method and Neural Network[J]. Journal of the Meteorology Society of Japan, 1998, 76 (5): 711-717.
[53] 覃志年，金龙．况雪源．人工神经网络的短期气候定性预测方法研究[J]．气象科技，2004，32(3)：168-172．
[54] 李柞泳，邓新民。人工神经网络在台风预报中的应用初探[J]．自然灾害学报，1995，4(2)：86-90．
[55] 陆虹，金龙．缪启龙等．影响广西热带气旋年频数的神经网络预测模型[J]．南京气象学院学报，2003，26(1)：56-62．
[56] 张韧，蒋国荣，余志豪等．利用神经网络计算方法建立太平洋副方的预报模型[J]．应用气象学报，2000，11(4)：474-483．
[57] 张韧．基于前传式网络逼近的太平洋副热带高压活动的诊断预测[J]．大气科学，2001，25(5)：650-660．
[58] 蔡煜东，宫家文，甘骏人等。运用人工神经网络作汛期降水预报[J]．气象科学，1994，14(4)，386-389．
[59] 盛永宽．短期气象(月、季、年)逐月降水系统研究[J]．气象．1996．22(1)：3-8．
[60] 金龙，陈宁，林振山．基于人工神经网络的集成预报方法研究和比较[J]．气象学报，1999，57(2)：198-207．
[61] 郭光，严绍瑾，尹树新．人工神经网络用于我国东部汛期降水预测的研究[J]．南京气象学院学报，1996，19(3)：354-357．
[62] David Silverman, John A. Dracup. Artificial Network and Long-range Precipitation in California[J], Journal of Apllied Meteorology, 2000, 39(1): 57-66.
[63] 熊秋芬，王丽．湖北省常规天然要素分县MOS预报效果检验[J]．湖北气象，2000，(4)：13-16．
[64] JIN Long, KONG Xueyuan, HUANG Haihong. Study on the Overfitting of the Artificial Neural Network Forecasting Model[J]. ACTA METEOROLOGICA SINCA, 2005, 19(2): 216-225.
[65] 胡江林，张礼平，宇如聪．神经网络模型预报湖北汛期降水量的应用研究[J]．气象学报，2001，59(6)：776-783．
[66] 金龙，罗莹，王业宏．月降水量的神经网络混合预报方法[J]．高原气象，2003．22(6)：618-623．
[67] 王业宏，金龙．基于自然正交展开的神经网络长期预报模型[J]．自然灾害学报，2003，12(2)．127-132．
[68] 张承福．人工神经网络在天气预报中的应用[J]．气象，1994，20(6)，43-47．
[69] 姜天戟，袁曾任．新激活函数下前馈型神经网络及其在天气预报中的应用[J]．信息与控制，1995，24(1)：47-51．
[70] Tony Hall. Precipitation Forecasting Using a Neural Network[J], Weather and Forecasting. 1999, 14(3): 338-345.
[71] Tim Bellerby, Martin Todd, Dom Kniveton. Chris Kidd, Rainfall Estimation from a Combination of TRMM Precipitation Radar and GEOS Multispectral Satellite Imagery through the Use of an Artificial Neural Network[J]. Journal of Applied Meteorology, 2000, 39 (12): 2115-2128.
[72] Hongping Liu, V. Chandrasekar, and Gang Xu. An adaptive Neural Network Schema for Radar Rainfall Estimation from Wsr-88d Observations[J]. Journal of Applied Meteorology, 2001, 40(11): 2038-2050.
[73] 师春香，卢乃锰，张文建．卫星面雨量估计人工神经网络方法[J]．气候与环境研究．2001，6(4)：467-472．
[74] 熊秋芬，胡江林，展军．神经网络方法在静业卫星多通道资料估算降水中的应用[J]．气象，2002．28(9)：17-21．
[75] 胡江林，涂松柏，冯光柳．基于人工神经网络的暴雨预报方法探讨[J]．热带气象学报，2003，19(4)：422-428．
[76] Auroop R. Ganguly, Rafael L. Bras, Distributed Quantitative Precipitation Forecasting Using Information from Radar and Numerical Weather Prediction Models[J]. Journal of Hydrometeorology, 2003, 4(6):1168-1180.
[77] Roderick A. Scofield, Robert J. Kuligowski. Status and Outlook of Operational Satellite Precipitation Algorithms for Extreme-Precipitation Events[J]. Weather and Forecasting, 2003, 18(6):1037-1051.
[78] T. J. Bellerby. A Feature-Based Approach to Satellite Precipitation Monitoring Using Geostationary IR Imagery[J]. Journal of Hydrometeorology, 2004, 5(5): 910-921.
[79] 桂海林，郁凡．用神经网络进行多波段卫星信息的降水估测[J]．气象科学，2004，24(2)：177-184．
[80] Francisco J. Tapiador, Chris Kidd, Vincenzo Levizzani, and Frank S. Marzano. A Neural Networks-Based Fusion Technique to Estimate Half-Hourly Rainfall Estimates at 0.1° Resolution from Satellite Passive Microwave and Infrared Data[J]. Journal of Applied Meteorology, 2004, 43(4): 576-594.
[81] 段婧，苗春生．人工神经网络在梅雨期短期降水分级预报中的应用[J]．气象，2005，31(8)：31-36．
[82] 胡波，杜惠良，滕卫平，肖云．用红外云图估算热带气旋短时雨量[J]．气象，2006，32(1)：74-77．
[83] 林健玲．金龙，彭海燕．区域降水数值预报产品人工神经网络释用预报研究[J]．气象科技．2006，34(1)：12-17．
[84] 林健玲，金龙，林开平．神经网络方法在广西日降水预报中的应用[J]．南京气象学院学报，2006，29(2)：215-219．
[85] Arnold F Shapiro. The merging of neural net-works, fuzzy logic and genetic algorithms[J]. Insurance: Mathematics and Economics, 2002, 31:115-13t.
[86] Blanco A, Delgado M, Pegalajar M C. A real-coded genetic algorithm for training recurrent neural networks[J]. Neural Networks, 2001, 14: 93-105.
[87] V. Lakshmanan. Speeding Up a Large-Scale Filter[J]. Journal of Atmospheric and Oceanic Technology, 2000, 17(4): 468-473.
[88] Henry K. Ntale, Thian Yew Gan, and Davison Mwale. Prediction of East African Seasonal Rainfall Using Simplex Canonical Correlation Analysis[J]. Journal of Climate, 2003, 16(12): 2105-2112.
[89] 王秀春，智会强．人工神经网络和遗传算法在导热反问题中的应用[J]．河北工业大学学报，2004，33(2)：171-176．
[90] 陈海英，郭巧，徐力．基于混合遗传神经网络的百米跑成绩预测方法[J]．计算机仿真，2004，21(2)：89-92．
[91] 谢冰，戴盛，谢科范．基于遗传神经网络的工业股票指数预测[J]．湖南大学学报，2004，18(6)：59-64．
[92] 陈守煜，王大刚．基于遗传算法的模糊优选BP网络模型及其应用[J]．水利学报，2003，(5)：116-121．
[93] 罗长寿，左强，李宝国．基于遗传算法的人工神经网络模型在冬小麦根系分布预报中的应用[J]．应用生态学报，2004，15(2)：354-356．
[94] 郭章林，刘明广，解德才．震灾经济损失的神经网络模型[J]．自然灾害学报，2004，13(6)：92-96．
[95] 李爱云，吴建华，曹广学．遗传算法与神经网络在洪水预报中的应用[J]．太原理工大学学报，2005，36(5)：585-588．
[96] 李鸿雁，侯光明．提高洪水智能预报中洪峰预报精度方法的研究[J]．自然灾害学报，2004，13(4)：128-134．
[97] 林建宇．BP神经网络结合遗传算法进行股市预测的研究[J]．福建电脑，2005，(12)：91-92．
[98] 刘明广，郭章林．基于GA-ANN的震灾风险预测模型研究[J]．中国工程科学，2006，8(3)：83-86．
[99] 吴建生．旱涝灾害的遗传-神经网络集成预测方法研究[J]．广西科学，2006，13(3)：203-206．
[100] 洪梅，张韧，吴国雄，何金海，余丹丹．副热带高压强度变化的模糊聚类诊断预测[J]．应用气象学报，2006，17(4)：459-466．
[101] Miller GF, Todd PM and Hedge SU. Designing neural networks using genetic algorithm[C]. Proc. Of 3rd conf. On Arlington, 1989, 479-384.
[102] Harp SA, Samad T. Optimizing neural networks with genetic algorithms[C]. Proceedings of the American Power Conference, 1991, (11): 38-43.
[103] Goldberg D E. Genetic Algorithms in Search, Optimization, and Machine Learning[J]. Reading, MA, Addision Wisely, 1989.
[104] Back T. Schwefel H-P. An overview of evolutionary algorithms for parameter optimization[J]. Evolutionary Computation. 1993, (1): 1-23.
[105] Maniezzo V, Genetic evolution of the topology and weight distribution of neural networks[J]. IEEE, Trans. Neural Networks, 1994, (1): 39-53.
[106] 周娜，周燕屏．神经网络及遗传算法在径流预报中的应用[J]．计算机仿真，2004，21(9)：117-119．
[107] 李爱云，吴建华．神经网络在径流水量还原计算中的应用[J]．东北水利水电，2006，24(1)：9-11．
[108] 金龙，吴建生，林开平，陈冰廉．基于遗传算法的神经网络短期气候预测模型[J]．高原气象，2005，24(6)：981-987．
[109] 谷晓平，王长耀，袁淑杰．GA-BP神经网络模型在流域面雨量预报的应用研究[J]．热带气象学报，2006，22(3)：248-252．
[110] Baum E B, Hausster D. What size net gives valid generalization[J]. Neural Computation, 1989, (1): 151-160.
[111] Moody, J.E.. The effective number of parameters: An analysis of generalization and regularization in nonlinear learning system[J]. Adv. Neural Inf. Process. Syst. 1992, 4:848-854.
[112] Barron A R. Approximation and estimation bounds for artificial neural networks [J]. Machine Learning, 1994, (14): 115-133.
[113] Cataltepe Z Abu-mostafa Y.S, Magdon-lsmail M No free lunch for earlystopping[J]. Neural Computation, 1999, 11: 995-100.
[114] Amari S, Muller K R, Asymptotic statistical theory of overtraining and cross-validation[J]. IEEE Transactions on Neural Networks, 1997, 8(5): 985-996.
[115] 胡耀垓，李凯扬，钟毓宁．一种改进的神经网络BP算法[J]．武汉大学学报(自然科学版)．1999，45(1)：25-29．
[116] 林俊，章兢．B-P网络泛化性能的改善[J]．计算机与现代化，2001，73(3)：1-5．
[117] 李俭川，秦国军，温熙森．神经网络学习算法的过拟合问题及解决方法[J]．振动、测试与诊断，2002，22(4)：260-264．
[118] 武妍，张立明．神经网络的泛化能力与结构优化算法研究[J]．计算机应用研究，2002，19(6)：21-25．
[119] 李祚泳．彭荔红．BP网络学习能力与泛化能力满足的不确定关系式[J]．中国科学：E辑 2003，33(10)：887-895．
[120] 殷春霞，胡雪松，郭元裕等．改善径向基函数网络泛化性能的主成分分析方法及应用研究[J]．武汉水利电力大学学报，2000，33(2)：85-89．
[121] 江学军，唐焕文．前馈网络泛化性能力的系统分析[J]．系统工程理论与实践，2000，20(8)：36-40．
[122] 杨晓红，刘乐善．用遗传算法优化神经网络结构[J]．计算机应用与软件，1997，14(3)：59-65．
[1] 朱翚．芮延年．严红．基于人工模糊神经网络高速造纸机多机同步智能控制[J]．电机一体化，2006，12(1)：60-62．
[2] 秦宏伍，庄乾章．神经网络专家系统协同式智能控制系统结构[J]．长春大学学报，2004，14(6)：14-16．
[3] 沈国江，王智，刘翔，孙优贤．城市区域交通智能控制研究[J]．信息与控制，2004，14(6)：14-16．
[4] 蒋天发，王江晴．神经网络PID复合智能控制参数自整定研究[J]．武汉大学学报(工学版)，2003，36(4)：111-114．
[5] Pappis C P, Mamdani E H. A fuzzy logic controller for atraffic junction[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1997, 7(10):707-717.
[6] Lee J H, Lee K M, Leekwang H. Traffic control of intersection group based on Fuzzy logic[C]. Proceedings of the 6th International Congress on Fuzzy System, 1995: 465-468.
[7] Paoram De., Amodified Smith. Oredictor and controller for unstable processes with delay[J], control, 1995, 41(4): 1025-1036.
[8] Straub S, Schroder D. Identification of nonlinear dynamic systems with recurrent neural networks and Kalman filter methods[C]. IEEE ISCAS' 96. 1996, 3: 341-344.
[9] Korbicz J, Janczk A. A neural network approach to identification of structural systems[C]. IEEE ISLE'96, 1996,1: 98-103.
[10] 文卉．王创新．基于神经网络算法的频谱分析[J]．湖南师范大学自然科学学报，2006，29(1)：47-51．
[11] 谭德荣．韩加蓬．基于BP的车辆系统故障诊断模式识别[J]．山东理工大学学报，2003，17(3)：8-12．
[12] HO T K, Hull J J, Srihari S N. Decision combination in multiple classifier system[J]. IEEE Trans on PAMI, 1994, 16(1):66-75.
[13] Grossberg S. Nonlinear Neural Networks: Principles, Mechanisms and Architectures[J]. Neural Networks, 1998, 1(1): 47-61.
[14] 黄雪梅．唐治德，赵一凡，舒志强．BP网络研究及其在肺癌诊断系统中的应用[J]．重庆大学学报(自然科学版)，2005，28(1)：42-44．
[15] Falchini M, Stecco A, Carmicnani L. Neural Network Based Detection of Pulmonary Nodules on Chest Radiographs[J]. Radio Med, 1999, 98(4): 259-263.
[16] Nakamura K, Yoshida H, Engelmann R. Computerized Analysis of the Likelihood of Malignancy in Solitary Pulmonary Nodules with Used of Artificial Neural Networks[J]. Radiology, 2000, 214(3): 823-830.
[17] 蒋宗礼．人工神经网络导论[M]．北京：高等教育出版社．2001．
[18] Martin T．Hagan，Howard B．Demuth．Mark H．Beale著．戴葵等译．神经网络设计[M]．北京：机械工业出版社，2002．
[19] Simon Haykin著，叶世伟，史忠植译．神经网络原理[M]．北京：机械工业出版社，2004．
[20] Hecht-Nielsen R. Application of counter-propagat ion network[J]. Neural Network, 1988, 1(2): 131-140.
[21] 徐丽娜．神经网络控制[M]．哈尔滨：哈尔滨工业大学出版社，2003．
[22] 王旭，王宏等．人工神经网络原理与应用[M]．沈阳：东北大学出版社，2000．
[23] 闻新，周露等，Matlab神经网络仿真与应用[M]．北京：科学技术出版社，2003．
[24] 高隽．人工神经网络原理及仿真实例[M]．北京：机械工业出版社，2003．
[25] 从爽．面向Matlab工具箱的神经网络理论与应用[M]．合肥：中国科学技术大学出版社，1998．
[26] 周继成等．人工神经网络—第六代计算机的实现[M]．北京：科学普及出版社，1993．
[27] 周继成．人工神经网络进展(Ⅰ)[J]．应用声学，1991，10(5)：39-46．
[28] 周继成．人工神经网络进展(Ⅱ)[J]．应用声学，1991，10(6)：39-42．
[29] Hebb D O. The Organization of Behavior[M]. New York: Wiley, 1949.
[30] F. Rosenblatt. Storage and Organization in the brain[J]. Psychological Review, 1958, 65(6): 386-392.
[31] 周抚生，李春龙．人工神经网络简介及在油田土建工程中的应用展望[J]．油气田地面工程，1999，18(1)：63-67．
[32] Derek F., stubbs M. D. Neurocomputer[M]. Published with permission of springer-verlag international publications june, 1989.
[33] Frank Rosenblatt. Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms[M]. Spartan Books, Washington, DC, 1962.
[34] Grossberg, S. Nonlinear difference-differential equations in prediction and learning theory[J]. Proceedings of the National Academy of Sciences, 1967, 58: 1329-1334.
[35] Marvin Minsky. Seymour Papert. Perceptrons[M], The MiT Press, Expand edition, 1969.
[36] Grossberg, S.. Some physiological and biochemical consequences of psychological postulates[J], Proceedings of the National Academy of Sciences, 1968, 60: 758-765.
[37]Grossberg, S. . Some networks that can learn, remember, and reproduce any number of complicated space-time patterns[J]. Journal of Mathematics and Mechanics, 1969, 19: 53-91.
[38]Grossberg, S. . On learning of spatiotemporal patterns by networks with ordered sensory and motor components[J]. Excitatory components of the cerebellum. Studies in Applied Mathematics, 1969, 48: 105-132.
[39]Kohonen, T. Self-Organization and associated memory [M]. Berlin: Springer-Verlag, 2nd Edition, 1987:1-65.
[40]Teuvo Kohonen, Panu Somervuo. Self-organizing maps of symbol strings[J]. Neurocomputing, 1998, 21:19-30.
[41] J. J. Hopfield, F. A. Ferrone. Rate of quarternary structure change in hemoglobin measured by modulated excitation[J]. PNAS 73, 1976: 4497.
[42]J.J. Hopfield Electron Transfer Between Biological Molecules by Thermally Activated Tunneling [J]. PNAS 71, 1974: 3640-3644.
[43]Anderson J A., Silverstein J W, Ritz S A, et al. Distinctive features, categorical perception and probability learning: Some applications of a neural model in Neurocomputing: Foundations of Research, Anderson J A and Rosenfeld E.Eds. Cambridge, M A: MIT Press, 1988: Ch. 2-Ch. 4.
[44]Golden R M. The Brain-State-in-a-Box neural model is a gradient descent algorithm[J]. Journal of Mathematical Psychology, 1986, 30(1): 73-80.
[45]Greeberg H J. Equilibria of the Brain-in-a-Box (BSB) neural model [J]. lEEE Trans on Neural Networks, 1988, 1(4): 323-324.
[46]Rumelhart D E, Williams R J. Learning representations by back-propagation errors[J]. NATURE, 1986, 323: 533-536.
[47]JohnJ. Hopfield. Neural networks and physical systems with emergent collective computational abilities[J]. PNAS 79, 1982, 2554.
[48]Hopfield J J. Neurons with Graded Respone have Collective Computational Properties Like those of Twostate Neurons [J]. Proc, Natl, Acd. Sci, 1984, 81: 3088-3092.
[49]Hopfield J J, Tank D W. Computing with Neural Circuits: A Model [J]. Science, 1986, 233: 625-633.
[50]Rumelhart D E. , Hinton G. E. , Williams R.J.. Learning Internal Representations by Error Back Propagation, in D. E. Rumelhart and L. L. McClelland (eds. ) , parallel Distributed Processing: Explorations in the Microstructure of Cognition Vol, 1, Foundations, The MIT Press, Ch8, 1986.
[51] Simon Haykin著，叶世伟，史忠植译．神经网络原理[M]．北京：机械工业出版社．2004．
[52] 金龙．神经网络气象预报建模理论方法与应用[M]．北京：气象出版社，2004．
[53] 党建武．神经网络技术及应用[M]．北京：中国铁道出版社．2000．
[54] 徐丽娜．神经网络控制[M]．北京：电子工业出版社．2003．
[55] 焦李成．神经网络系统理论[M]．西安：西安电子科技大学出版社，1990．
[56] 胡守仁，沈清，胡德文等．神经网络应用技术[M]．长沙：国防科技大学出版社，1993
[57] Kurt Hornik. Approximation capabilities of multilayer feedforward networks[J]. Nueral Networks, 1991, 4(2): 251-257.
[58] 尚钢，钟珞，陈立耀．神经网络结构与训练参数选取．[J]．武汉工业大学学报，1997，19(2)：108-110．
[1] Holland J H. Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence[M]. 1st edition, Ann Arbor, MI: The University of Michigan Press, 1975.
[2] Holland J H., Reitman J.S.. Cognitive systems based on adaptive algorithms, Pattern-directed Inference System[M]. NY: Academic Press, 1978.
[3] Goldberg DE., Genetic algorithms in search, optimization, and machine learning[M]. Reading, MA: Addison-Wesley, 1989.
[4] Goldberg DE., Deb K. A comparative analysis of selection schemes used in genetic algorithms[A]. Rawlins G. Foundations of genetic algorithms[C]. San Mateo, CA: Morgan Kaufmann, 1991.
[5] Goldberg DE, Korb B., Deb K.. Messy genetic algorithms: motivation, analysis, and 3rst results[J]. Complex Systems, 1989, (3): 493-530.
[6] 周明，孙树栋．遗传算法原理及其应用[M]．北京：国防工业出版社，1999：35-47．
[7] 张文修．梁怡．遗传算法的数学基础[M]．西安：西安交通大学出版社，2003．
[8] 胡兰萍，黄海斌．遗传算法及其在化学领域中的应用[J]．海南师范学院学报(自然科学版)，2006，19(3)：261-266．
[9] 祝江汉，李曦，毛赤龙，张利宁．多卫星区域观测任务的侧摆方案优化方法研究[J]．武汉大学学报(信息科学版)，2006，31(10)：868-870．
[10] 毛斌，张齐凯，卢海林．基于遗传算法的江汉平原CFG桩复合地基优化设计研究[J]．长江大学学报(理工卷)，2006，3(13)：97-99．
[11] 周湶，孙才新，张晓星等．基于多种群免疫遗传算法的配电网网架规划[J]．重庆大学学报(自然科学版)，2005，28(4)：36-41．
[12] 钟胜，王朝金，闻英友等．遗传算法在CDMA网络基站分布规划中的应用[J]．邮电设计，2004，(6)：9-13．
[13] Wang Jian, Zhou Jiangqi, Lin Zhongqin. Locators Optimization for Measuring Fixture Design[J]. Chinese Journal of Mechanical Engineering, 2004, 17(3):332-335.
[14] 马小明，曹云等．基于随机优化方法的大气污染物总量控制模型[J]．中国环境科学，2001，21(5)：436-439．
[15] 陈国良，王熙法．遗传算法及其应用[M]．北京：人民邮电出版社，1996．
[16] 王小平．曹立明．遗传算法—理论应用与软件实现[M]．西安：西安交通大学出版社，2002：15-17．
[17] Goldberg D. F, Real Coded Genetic Algorithm, Virtual Alphabcts and Blocking. Complex Systems, 1991 (5): 139-167.
[18] 余有明，刘玉树，阎光伟．遗传算法的编码理论与应用[J]．计算机工程与应用，2006，(3)：86-89．
[19] Raul T S., Julio C H, Alex A F. Extracting Comprehensible Rules from Neural Networks via Genetic Algorithm[J]. IEEE. 2000, 36: 130-139.
[20] 国嘉，王瑞敏．王家海．张忠民．基于遗传算法的神经网络学习方法[J]．计算机与数字工程，2004，32(5)：101．
[21] 李士勇．李盼池．基于实数编码和目标函数梯度的量子遗传算法[J]．哈尔滨工业大学学报，2006，38(6)：1216-1218．
[22] 徐静波．一种融合神经网络学习的遗传算法[J]．上海工程技术大学学报，2000，14(3)：173-177．
[23] 周娜，周燕屏．神经网络及遗传算法在径流预报中的应用[J]．计算机仿真，2004，21(9)：117-119．
[24] 杨献波，程建川，冯云飞．公路纵断面优化的遗传算法设计[J]．交通与计算机，2005，23(3)：16-19．
[25] Bagley J. D. The behavior of adaptation system which employ genetic and correlation algorithm[J], Dissertation abstracts international: 1967, 28(12).
[26] De Jong K A. An analysis of the behavour of aclassof genetic adaptive systems [D]. University of Michigan, 1975: 76-9381.
[27] Goldberg D E. Genetic Algorithms in Search, Optimization, and Machine Learning[J]. Reading, MA, Addision Wisely, 1989.
[28] Davis, L. D. Handbook of genetic algorithms[M], Van Nostrand Reinhold, 1991.
[29] Koza, J. R. Genetic programming1 [M]. Cambridge, MA: the MI Press, 1992.
[30] Michalewicz Z. Genetic Algorithms+Data Structures=Evolut on Programs[M]. Springer-Verlag, Second, Extended Edition, 1994.
[31] Hofbauer J, Sigmud K. The Theory of Evolution and Dynamical Systems[M]. Cambrige University Press, 1989.
[32] John. J. Hopfield, Dawei Dong.. Dynamic properties of neural networks with learning and feedback[J]. Network, 1992, (3):267-283.
[33] 李通化 张众杰．用数值遗传算法计算配合物的稳定常数[J]．高等学校化学学报，1995，16(3)：354-358．
[34] Lucasius C B, Beckers M L M, Kateman G. Genetic algorithms in wavelength s election: a comparative study[J]. Analytica Chimica Acta, 1994, 286: 135-153.
[35] D. Wienke, C. B. Lucasius and G. Kateman. Multicriteria target vector optimization of analytical procedures using a genetic algorithm. Part Ⅰ. Theory, numerical simulation and application to atomic emission spectroscopy[J], Analytica Chimica Acta, 1992, 265: 211-225,
[36] D. Wienke, C. B. Lucasius and G. Kateman, Multicriteria target vector optimization of analytical procedures using a genetic algorithm. Part Ⅱ. Polyoptimization of the photometric calibration graph of dry glucose sensors for quantitative clinical analysis[J], Analytica Chimica Acta, 1993, 271: 253-268.
[37] Cieniawski S E, Eheart J W, Ranjithan S. Using genetic algorithms to solve a multiobjective groundwater monitoring problem[J]. Water Resour Res, 1995, 31(2):399-409.
[38] Melanie Mitchell. An introduction to genetic algorithms[M]. Cambridge, MA: The MIT Press, 1996.
[39] Kadaba, N., Nygard, K.E.,and Juell, P. J.,Integration of adaptive machine learning and knowledgecased systems for routing and scheduling applications[J]. Expert Systems with Application, 1991, 2(1):15-27.
[40] Lin, S. H., Goodman, E. D., and Paunch, W. F., Investigating Parallel Genetic Algorithms on Job Shop Scheduling Problem[C]. In the Sixth International Conference on Evolutionary Programming, Angeline, P., Reynolds, R. J. M., and Eberhart, R. (ed.), Berlin: Springer-Verlag, 1997: 383-393.
[41] Cartwright H M, Long R A. Sumultaneous optimization of chemical flowshop sequencing and topology using genetic algorithms[J]. Ind Eng Chem Res, 1993,
32:2706-2713.
[42]Syswerda G. Study of reproduction in generational and steadystate genetic algorithms[J]. San Mateo, CA: Morgan Kaufmann. 1991: 94-101.
[43]Hilliard M R, Liepins G E. Mark Palmer, and Michael Morrow. Greedy genetics. Proc. of the 2nd Int'l. Confi. On Genetic Algorithms, 1987: 28-31.
[44]Gabbert P S. A system for learning routes and schedules with genetic algorithms[C]. In:ICGA' 91,1991: 430-436.
[45]Dechaine MD, Feltus MA. Nuclear Fuel Management Optimization Using Genetic Algorithms[J]. Nucl. Tech, 1995, 111:109-114.
[46]Lin J, Bartal Y, Uhrig R E. Predicting the severity of NPP transients using nearest neighbors modeling optimized by genetic algorithms on a parallel computer [J]. Nucl Techol, 1995, 111:46-61.
[47] Cox CS, French IG, Ho CK Improved Ml MO System-Identification and Control Using Genetic Algorithms[J]. Chemical Engineering Research & Design, 1996, 74(1) : 97-105.
[48] 邓勃,刘嘉.遗传算法在分析化学中的应用[J].分析科学学报. 1997, 13(2) : 160-168.
[49]V.O. de Haan and. G. G. Drijkoningen. Genetic algorithms used in model finding and fitting for neutron reflection experiments[J]. Physica B, 1994, 198: 24-26.
[50]Kaufman, L. , Rousseeuw, P. J. Finding Groups in Data: An Introduction to Cluster Analysis[M]. John Wiley & Sons, New York, USA, 1990.
[51]Lucasius CB, Dane AD, Kateman G. On k-medoid cluster ing of large data sets with the aid of a genetic, algorithm: background, feasibility and comparison[J]. Anal. Chim. Acta 1993; 282: 647-669.
[52] Lucasius CB, deWeijer A P, Buydens L M C, Kateman G. CFIT: a genetic algorithm for survival of the fitting[J], Chemom. Intell. Lab. Syst. , 1993, (19) : 337-341.
[53]Lucasius, C. B. and Kateman, G. Gates towards Evolutionary Large-Scale Optimisation: A Software-Oriented Approach to Genetic Algorithms [J]. Computers and Chemistry 1994, 18, 137-156.
[54]Maclay, D. , and Dorey, R. Applying genetic search techniques to drivetrain modeling[J]. IEEE Control Systems, Special Issue on Intelligent Control, 1993, 13(3): 50-55.
[55] Freeman, L. M., et al. Turning fuzzy logic controller using geneticalgorithms aerospace applications[C]. In Proceedings of the AAAIC'90 Conference, Dayton, Oct., 1990:351-358.
[56] McCallum, R. A.,and Spackman, K. A. Using genetic algorithm to learn disjunctive rules form examples[C]. In Proceeding of the International Conference on Machine Learning, San Mateo, CA: Morgan Kaufmann, 1990: 149-152.
[57] TERJEB, JON A G. Natural language analysis for semantic documant modeling[J]. Data &Knowledge engineering, 2005, 38(1): 45-62.
[58] THOMSON W T. On-line MCSA to diagnose shorted turns in low voltage stator windings of 3-phase induction motors prior to failure[A]. International Conference for IEEE IEMDC01[C]. Atlanta, USA, 2005.
[59] Bennett, K., A genetic algorithm for database query optimization[C]. IEEE conference on Evolutionary Computation, 1994: 400-407.
[60] KOCKA T, CASTELOR. Improved learning of Bayesian network[A]. Breese j, Koller D. Uncertainty in Artificial Intelligence: Proceedings of the Seventeenth Conference (UAI'2001) [C]. San Francisco, US: M Kaufmann, 2001, 269-276.
[61] Xin Yao. A review of evolutionary artifical neural network[J]. International Journal of Intelligent Systems, 1993, 8(3): 539-565.
[62] Montana, D.J.,and Davis, L..Training feed-forward neutral networks using genetic algorithms [C]. In Proceeding of the International Joint Conference on Artificial Intelligence, Los Altos, CA: Morgan Kaufmann Publishers, 1989: 762-767.
[63] 张材，谭建平．基于遗传算法-反向传播模型的板形模式识别[J]．中南大学学报(自然科学版)．2006，37(2)：294-299．
[64] Tai J C, Tseng S T, et al. Real-Time Image Tracking for Automatic Traffic Monitoring and Enforcement Applications[J]. Image and Vision Computing, 2004, 22[6]:485-501.
[65] Pal N R, Bezdek J C. On cluster validity for the fuzzy C-means[J]. IEEE Transactions on Fuzzy System, 1995,3(3): 370-379.
[66] Bala, J., De Jong, K.A., Haung, J., Vafaie, H., and Wechsler, H. Hybrid learning using genetic algorithm and decision trees for pattern classification[J]. In Proceedings of the 14th International Joint Conference on Artificial Intelligence, August 19-25, 1995, Montreal, Canada.
[67] 宋立新．王玉华，李玲远．基于遗传算法和神经网络优化的故障诊断专家系统[J]．华中师范大学学报(自然科学版)，2005，39(3)：332-335．
[68] Abdelhadi B, Benoudjit A, Naitsaid. N. Application of genetic algorithm with a novel adaptive scheme for the identification of induction machine parameters[J]. IEEE Transaction on Energy Conversion, 2005, 20(6): 284-291.
[69] Nikolopoulos, C., and Fellrath, P., et al. Hybrid expert system for investment advising[J]. Expert System, 1994, 11(4): 245-248.
[70] 李敏强．寇纪凇等．遗传算法的基本理论与应用[M]．北京：科学出版社，2002．
[71] Goldberg, D. E., Segrest, P. Finite Markov Chain Analysis of Genetic Algorithms[C]. Proc. Of Second International Conference on Genetic Algorithms. 1987: 1-8.
[72] Eiben, A. E., Aarts, E. H., and Van Hee, K. M., Global Convergence of Genetic Algorithms; An Infinite Markov Chain Analysis. Parallel Problem Solving from Nature[M]. Berlin: Spring-Verlag, 1991: 4-12.
[73] Rudolph, G.. Convergence Properties of Canonical Genetic Algorithms[J]. IEEE Trans. On Neural Networks. 1994, 5(1): 96-101.
[74] Qi X., Palmieri F. Theoretical Analysis of Evolutionary Algorithms with an Infinite Population Size in Continuous Space, Part Ⅰ: Basic Properties of selection and Mutation[J]. IEEE Trans. On Neural Network, 1994: 102-119.
[75] 恽为民，席裕庚．遗传算法的全局收敛性和计算效率分析[J]．控制理论与应用，1996，13(4)：455-460．
[76] 刘淳安．解非线性规划的多目标遗传算法及其收敛性[J]．计算机工程与应用，2006，42(25)：27-29．
[77] 罗小平，韦巍．关于生物免疫遗传算法收敛性的一般讨论研究[J]．浙江大学学报，2005，39(12)：2006-2011．
[78] 刘淳安．多目标遗传算法的收敛性研究[J]．西华大学学报(自然科学版)，2005，24(6)：22-25．
[79] 丁建立，陈增强，袁著祉．遗传算法与蚂蚁算法融合的马尔可夫收敛性分析[J]．自动化学报，2004，30(4)：629-634．
[80] 吴建生，农吉夫，金龙，李日光。遗传算法收敛性分析[J]，广西师范学院学报(自然科学版)，2004，21(1)：48-52．
[81] De Jong K A. Genetic algorithms: a 25 years perspective. Computational intelligence imitating life[B]. New Yourk: IEEE press 1994:125-136.
[1] 金龙，况雪源，黄海洪，覃志年．人工神经网络预报模型的过拟合研究[J]．气象学报，2004，62(1)：62-70．
[2] Wu Yan, Zhang Liming. A new regularization learning method for improving generalization capability of neural network[C], proceedings of 4th world congress on intelligent control and automation, Shanghai,2002, #: 2011-2015.
[3] Saito K, Nakano R. Second-order learning algorithm with squared penalty term[J]. Neural Computation, 2000,12(3):709-729.
[4] 魏海坤，徐嗣鑫，宋文忠．神经网络的泛化理论和泛化方法[J]，自动化学报，2001，27(6)：806-815．
[5] Baum E B, Haussler D, What Size Net Gives Valid Generalization?[J]. NIPS 1,1989, San Mateo, CA, 81-90.
[6] Turmon M J, Fine T L. Sample Size Requirement for Feedforward Neural Networks Classifiers[C]. In: IEEE 1993 Intern, Sympos. Inform. Theory, 432-438.
[7] Mass W. Neural nets with superlinear VC-dimension[J]. Neural Computation. 1994, (6): 877-884.
[8] VapmkV, Levin E, Lecun Y. Measuring the VC-dimension of learning machine[J], Neural Computation. 1994, (6):851-876.
[9]. Niyogo P, Girosi F. On the relationship between generalization error, hypothesis complexity, and sample complexity for radial has s function[J]. Neural Computation. 1996, (8):819-842.
[10] Girosi F., Jones M, Poggio T. Regularization theory and neural networks architecture[J]. Neural Computation. 1995, (7):219-269.
[11] 董聪，郭晓华．计算智能中若干热点问题的研究与进展[J]．控制理论与应用．2000，17(5)：691-698．
[12] Homik K. Approximation capabilities of multilayer feedforward networks[J]. Neural Netwoks, 1991, (4):551-557.
[13] 董聪，郦正能，夏人伟，何庆芝．多层前向网络研究进展及若干问题[J]．力学进展．1995，25(2)：186-196．
[14] 江学军，唐焕文．前馈神经网络泛化能力的系统分析[J]．系统工程理论与实践，2000 (8)：36-40．
[15] R Reed.Pruning Algorithms-A survey[J].IEEE Trans.Neural Networks,1993. (4):740-747.
[16] 张乃尧，阎平凡．神经网络与模糊控制[M]．北京，请华大学出版社，1998．
[17] Willam Finnoff, Ferdinand Hergert, Hans Georg Zimmermann. Improving Model Selection by Nonconvergent Methods[J]. Neural Networks, 1999,12(1):79-89.
[18] L Holmotrom, P Koistinen.. Using Additive Noise in Back- propagation Training[J]. IEEE Trains. Neural Networks, 1992,3(1):24-38.
[19] Moody J E. The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning System[J]. NIPS 4. 1992, San Mateo, CA:847-854.
[20] Barron A R. Approximation and estimation bounds for artificial neural networks[J]. Machine Learning, 1994, (14):115-133.
[21] Partridge D. Network generalization differences quantified[J]. Neural Networks. 1996,9(2): 263-271.
[22] 袁美英，周秀杰，陈威．人工神经网络在温度和降水预报中的应用[J]．黑龙江气象，2000(3)：17-19．
[23]．冯光柳，崔春光．三峡地区降水神经元方法预报系统[J]．气象，2000，26(8)：25-26．
[24] 熊秋芬，胡江林．神经网络方法在静止卫星多通道资料估算降水中的应用[J]，气象，2002，28(9)：17-21．
[25] Abu-mostafa Y S. A Method of Learning From Hints[J]. NIPS 5, 1993, San Mateo, CA: 73-80.
[26] Mackay D J C, Bayesian interpolation[J]. Neural Computation, 1992,(3):415-447.
[27]. Williams P M, Bayesian regularization and pruning using a laplace prior[J]. Neural Computation, 1995, (7):117-143.
[28]. Abu-Mostafa Y S. Hints and the VC-dimension[J]. Neural Computation, 1993, (5):415-447.
[29] Kolen J F., Pollack J B. Back Propagation is Sensitive to Initial Conditions[J] NIPS 3, 1991, San Mateo, CA:860-867.
[30] Schmudt W F, Raudys S, Kraaijveld M A et al. Initialization Back-propagation and generalization of feed-forward classifiers[J]. InProc. IEEE Int. Conf. Neural Networks, 1993, 598-604.
[31] Atiya A, Ji C Y. How initial conditions affect generalization performance in large networks [J]. IEEE Trans Neural Networks, 1997, 8(2):448～451.
[32] 董聪．人工神经网络：当前的进展与问题[J]．科技导报，1999，7：26-30．
[33] Reed R. Pruning algorithms: A survey[J]. IEEE Trans, Neural Networks, 1993, (4):740-747.
[34] Wang C, Venkatesh S. Optimal Stopping and Effective Machine Complexity in Learning[J]. NIPS 6.1994, San Mateo, CA:263-270.
[35] Tom M．Mitchell著．机器学习[M]．曾华军，张银奎等译．北京：机械工业出版社．2003．
[36] Levin E, N Tishby, S A Solia. A statistical approach to learning and generalization in layered neural networks[C]. Proc IEEE, 1990, 78(10):1568-1574.
[37] 董聪，刘西拉．广义BP算法及网络容错和泛化能力的研究[J]．控制与决策，1998，13(3)：120-124．
[1] 任宏利，高丽，张培群等，相空间中划分大尺度异常雨型的初步研究[J]．气象学报，2004，62(4)，459-467．
[2] Jin Long, Luo Ying, Guo Guang, et al. Study on mixed model of neural network for farmland flood/drought prediction[J], ActaMeteorological Sinica, 1997,11(3): 364-373.
[3] Tony Hall. Precipitation forecasting using a neural network[J]. Weather and Forecasting, 14(3): 338-345.
[4] Marzban C, Witt Arthur, Thiria S, et al. A Bayesian neural network for sever hail size prediction[J]. Weather and Forecasting, 2000,16(5): 600-610.
[5] Silverman D, Dracup J. Artificial network and long-rang Precipitation in California[J]. Journal of Applied Meteorology, 2000,31(1): 57-66.
[6] Jin Long, Qing Weiliang. Study on combination of ANN method with mean generation function for short-term climate prediction[C]. 8th International Conference on Neural Information Processing, Shanghai, China, Fudan University Press, 2001,2:981-985.
[7] din Long, du Weimin, Miao Qilong. Study on Ann-based multi-step prediction model of short-term climatic variation[J]. Advances in Atmospheric Sciences, 2000, 17(1):157-164.
[8] 段婧，苗春生．人工神经网络在梅雨期短期降水分级预报中的应用[J]，气象，2005，31(8)：31-36．
[9] 桂海林，郁凡．用神经网络进行多波段卫星信息的降水估测[J]，气象科学，2004，24(2)，177-184．
[10] 艾艳，汤志亚，王敏．基于8P神经网络的短期降水预报[J]．河南教育学院学报(自然科学版)，2004，13(3)：60-62．
[11] 李才媛，王仁乔，王丽等．长江上游流域短期强降水面雨量预报系统[J]，气象，2003，29(3)：34-37．
[12] 熊秋芬，胡江林，夏军．神经网络方法在静业卫星多通道资料估算降水中的应用[J]．气象，2002，28(9)，17-21．
[13] 牛文全，李靖．降水量的BP人工神经网络预测模型极其应用[J]．西北农林科技大学学报(自然科学版)，2001，29(4)：103-106．
[14] 师春香，卢乃锰，张文建．卫星面雨量估计人工神经网络方法[J]．气候与环境研究，2001，6(4)，467-472．
[15] 孙日丁，周官辉，杜滨鹤等．人工神经网络方法在鹤壁汛期降水预报中的应用[J]．河南气象，2004，(3)：12-13．
[16] 李伟钢，Maria，C V Ramjrez，Nelson J Ferreira，石立华，Leonardo D de A sa．气象卫星云图的多分辨小波分解及人工神经网络降水估计研究[J]，南京气象学院学报，2000，23(2)：277-282．
[17] 尚钢，钟珞，陈立耀．神经网络结构与训练参数选取[J]．武汉工业大学学报．1997，19(2)：108-110．
[18] Hechi-Nielsen, R. Theory of the back propagation neural network[C]. Int. J. Conf. On Neural Network, Washington D. C., 1989, (1): 593—605.
[19] 张立明．人工神经网络的模型及其应用[M]．上海：复旦大学出版社，1993，32-51．
[20] Kakeya H, Dkabe Y. Fast combinatorial optimization with parallel digital computers[J]. IEEE TRANSACTIONS on Neural Networks, 2000, 11(6): 1323-1331.
[21] 吕柏权，李天择．一种优化神经网络结构算法[J]．华北电力大学学报，1996，23(3)：36-40．
[22] Junichi Murata，Hiroshi Fujii，Kensuke Ikeda，Kotaro Hirasawa．A Structure Design Method for Multiayer Networks Based on Redundancy Test[C]．计测自动制御学会论文集(日本)，1995，32(2)：236-243．
[23] 马正华，薛国新．BP神经网络训练的改进[J]．江苏理工大学学报(自然科学版)，2000，21(1)：79-82．
[24] 高洪深，陶有德．BP神经网络的改进[J]．系统工程理论与实践，1996，(1)：67-71．
[25] 徐晋．基于重置的LM变结构BP神经网络[J]．系统工程理论与实践，2004，(1)：120-125．
[26] 林正炎，陆传荣．概率极限理论基础[M]．北京：高等教育出版社，2001．27-28．
[27] 林开平，金龙，林健玲．基于遗传—神经网络的数值预报产品在短期降水预报释用方法研究[J]．气象学报，2005，63(增刊)：23-28．
[28] 金龙，况雪源，黄海洪等．人工神经网络预报模型的过拟合研究．气象学报[J]，2004， 62(1)：62-70．
[29] 祝从文，TetsuoNakazawa，李建平．大气季节内震动对印度洋-西太平洋地区热带低压／气旋生成的影响[J]．气象学报，2004，62(1)，42-50．
[30] 林开平，孙崇智，郑凤琴等．丘陵地区面雨量计算方法及应用[J]．气象，2003．29(10)：8-16．
[31] 林开平，孙崇智，陈冰廉等．广西主要江河流域的面雨量合成分析与洪涝的关系[J]．热带地理，2003，23(3)：164-170．
[32] Sim D. Aberson, Charles R. Sampson. On the Predictability of Tropical Cyclone Tracks in the Northwest Pacific Basin[J]. Monthly Weather Review. 2003, 131 (7): 1491-1497.
[33] M. Bessafi, A. Lasserre-Bigorry. Statistical Prediction of Tropical Cyclone Motion: An Analog-CLIPER Approach[J]. Weather and Forecasting. 2002, 17(4): 821-831.
[1] JIN Long, KONG Xueyuan, HUANG Haihong. Study on the Overfitting of the Artificial Neural Network Forecasting Model[J]. ACTA METEOROLOGICA SINCA, 2005, 19(2): 216-225.
[2] 魏海坤，徐嗣鑫，宋文忠．神经网络的泛化理论和泛化方法[J]，自动化学报，2001，27(6)：806-8t5．
[3] Kowalczyk A, Ferra H. Generalization in Feedforward Networks[J]. NIPS 7, 1995, Cambridge, MA: 215-222.
[4] Barron A R. Approximation and estimation bounds for artificial neural networks[J]. Machine Learning, 1994, (14): 115-133.
[5] Pertridge D. Network generalization differences quantified[J]. Neural Networks, 1996, 9(2): 263-271.
[6] Cataltepe Z, Abu-Mostafa Y S, Magdon-lsmail M. No free lunch for early-stopping[J]. Neural Computation, 1999, (11): 995-1009.
[7] 张鸿宾．训练多层网络的样本数问题[J]．自动化学报，1993，19(1)：71-77．
[8] G D Magoulas, V P Plagiananakos, M N Vrahatis. Globally convergent algorithms with local learning rates[J]. IEEE Trans on Neural Networks, 2002, 13(3): 774-779.
[9] K Eom, K Jung, H Sirisena. Performance improvement of back-propagation algorithm by automatic activation function gain tuning using fuzzy logic[J]. Neurocomputing, 2003, 50: 439-460.
[10] 冯乃勤，王芳，丘玉辉．提高神经网络泛化能力的研究[J]．计算机工程与应用．2006，(4)：38-41．
[11] 武妍，王守觉．一种通过反馈提高神经网络学习性能的新方法[J]．计算机研究与发展．2004，41(9)：1489-1492．
[12] 刘青，周鹏．基于强泛化神经网络的大规模基因表达数据分析[J]．计算机工程．2005，31(3)．189-191．
[13] Reed R. Pruning algorithms: A survey[J]. IEEE Trans. Neural Networks, 1993,(4): 740-747.
[14] Kwok T Y, Yeung D Y. Constructive algorithms for structure learning in feedforward neural networks for regressing problems[J]. IEEE Trans. Neural Networks, 1997, (8): 630-645.
[15] Maniezzo V. Genetic evolution of the topology and weight distribution of neural networks[J]. IEEE Trans. Neural Networks. 1994, (5): 39-53.
[16] Murata N, Yoshizawa S, Amari S. Networks information criterion-determining the number of hidden units for an artificial neural network model[J]. IEEE Trans, Neural Networks, 1997, 5(6): 865-872.
[17] 黄山松，杜继宏，冯元昆．前向神经网络的处理能力和推广性量度[J]．清华大学学报(自然科学版，1999，39(7)：54-58．
[18] Treadgold N K, eedeon T D. Exploring Constructive Cascade Networks[J]. IEEE Transaction on Neural Networks, 1999, 10 (6): 1335-1350.
[19] Ponnapalli PVS, Ho K C, Thomson M. AFormal Selection and Pruning Algorithm for Feedforward Artificial Neural Network Optimization[J]. IEEE Transaction on Neural Networks, 1999, 10 (4): 964-968.
[20] 刘国东，丁晶．BP网络用于水文预测的几个问题探讨[J]．水利学报，1999，(6)：1-4
[21] 张文鸽，吴泽宁，逯洪波．BP神经网络的改进及其应用[J]．河南科学，2003，21(2)：2002-2006．
[22] Holmstrom L, Koistinen P. Using additive noise in backpropagation training[J]. IEEE Trans. Neural Networks, 1992, 3(1): 24-38.
[23] George N K. On overfitting, generalization, and randomly expanded training ser[J]. IEEE Trans. Neural Networks, 2000, 11(5): 1050-1057.
[24] 杨慧中，卢鹏飞，张素贞，陶振麟．网络泛化能力与随机扩展训练集[J]．控制理论与应用．2002，19(6)：963-966．
[25] 李杰，韩正之．神经网络的学习误差函数及泛化能力[J]．控制与决策，2000，15(1)：95-97．
[26] Sietsma J, Dow R J F. Creating artificial neural networks that generalization[J]. Neural Networks, 1991, (4): 67-79.
[27] Bishop C M. Training with noise is equivalent to Tikhonov regularization[J]. Neural Computation. 1995, (7): 108-116.
[28] An G. The effect of adding noise during backpropagation training on a generalization performance[J]. Neural Computation. 1996, (8): 643-671.
[29] Sjoberg J, Ljung L. Overtraining, regularizationand searching for aminimum, with application to neural networks[J]. International Journal of Control, 1995, 62(6): 1391-1407.
[30] Cataltepe Z, Abu-Mostafa Y S, Magdon-Ismail M. No free lunch for earlystopping[J]. Neural Computation. 1999, (11): 995-1009.
[31] 武美先，张学良，温淑花，李海楠．BP神经网络及其改进[J]．太原科技大学学报，2005，26(2)：201-130．
[32] 马正华，薛国新．BP神经网络训练的改进[J]．江苏理工大学学报(自然科学版)，2000，21(1)：79-82．
[33] 董武，李树祥，沈振康．神经网络BP学习算法的改进[J]．中国医学物理学杂志，1997，14(1)：23-25．
[34] 周凤利，李绍滋，梁文林．一种改进的BP算法[J]．电器传动自动化，1997，19(2)：39-41．
[35] 朱宏平，张源．基于自适应神经网络的结构损伤检测[J]．力学学报，2003，35(1)：110-115．
[36] 宋宜斌，王培进．多层前馈神经网络改进算法及其应用[J]．计算机工程，2003，29(14)：109-111．
[37] 周龙，詹琼华．多层前馈神经网络中改进BP算法的研究[J]．武汉食品工业学院学报，1999，(1)：69-74．
[38] 庞元明，施卫东．BP神经网络震荡和平台问题的解决[J]．北京理工大学学报，1995，15(5)：72-77．
[39] 姜绍飞，张春丽，钟善桐．BP网络模型的改进方法探讨[J]．哈尔滨建筑大学学报．2000，33(5)：57-60．
[40] 陈善广，鲍勇．BP神经网络学习算法研究[J]．应用基础与工程科学学报，1995，(4)：437-442．
[41] 王铁，陈进．BP算法中学习率及形状因子对学习速度的综合影响[J]．上海交通大学学报，1997，31(3)：109-112．
[42] 吴佑寿．一种激励函数可调的新人工神经网络及应用[J]．中国科学(E辑)，1997，(1)： 55-59．
[43] 张胜，刘红星，高敦堂，王蔚．神经网络泛化特性改善方法[J]．计算机应用与软件．2005，22(12)：12-14．
[44] Gencay-R, Qi-M. Pricing and Hedging Derivative Securities with Neural Networks-Bayesian Regularization, Early Stopping and Bagging[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12(4): 726-734.
[45] Lampinen-J, Vehtari-A. Bayesian-Approach for Neural Networks-Review and Case-Studies[J], Neural Netwoks, 2001, 14(3): 257-274.
[46] Leung-CT, Chow-TWS. Least 3rd-Order Cumulant Method with Adaptive Regularization Parameter Selection for Neural Networks[J], Artificial Intelligence, 2001, 127(2): 169-197.
[47] WANG-ZO, ZHU-T. An Efficient Learning Algorithm for Improving Generalization Performance of Radial Basis Function Neural Networks[J]. Neural Networks, 2000, 13(4): 545-553.
[48] Harris Druck, Yann Le Cun. Improving Generalization Using Double Backpropagation[J]. IEEE Trans. Neural Networks, 1992, 3(6): 991-997.
[49] 付秀琢，王兆辉．基于实例改进的BP算法的联合应用[J]．山东交通学院学报，2004，12(1)：33-36．
[50] 叶东毅．基于模型逼近度和接受概率的一个变步长快速BP学习算法[J]．计算机学报，1996，(10)：738-787．
[51] 叶东毅，何萧玲．前馈神经网络的一个改进的BP学习算法[J]．福州大学学报(自然科学版)，1998，26(2)：22-26．
[52] 张茂元，卢正鼎．基于李雅普诺夫函数的BP神经网络算法的收敛性分析[J]．小型微机计算机系统，2004，25(1)：93-95．
[53] 张海燕，胡光锐，张东红．多层前向神经网络的一种改进BP算法[J]．通讯技术，2003，(11)：6-7．
[54] 裴浩东，苏宏业，褚健．多层前向神经网络的权值平衡算法[J]．电子学报，2002，30(1)：139-141．
[55] 张学良，温淑花，武美先．前向神经网络的一种快速学习算法[M／CD]．第十三届全国神经网络学术大会，2004，10．
[56]Martin R, Heinrich B. A Direct Adaptive Method for Faster Back Propagation Learning: The RPROP Algorithm[A], Ruspini H. Proceedings of the IEEE International Conference on Neural Net works(ICNN)[C]. IEEE Press, New York. 1993, 586-591.
[57]Kennedy J , Eberbart R C. Particle swarm optimization[C], Proc IEEE international conference on Neural Networks. USA:IEEE Press, 1995, (4): 1942-1948.
[58] Kaiping Lin, Long Jin, Jianling Lin, Binglian Chen. The Relationship Between the Multi-Collinearity and the Generalization Capability of the Neural Network Forecast Model [C]. Sixth World Conference on Intelligence Control and Automation, IEEE Press ,2006, 12(1):56-60.