Abu-Mostafa Y S.Learning from hints in neural networks[J].Journal of Complexity,1990,6:192-198.
[2]
Moody J S.The efficient number of parameters:An analysis of generalization and regularization in nonlinear learning system[J].San Mateo,NIPS4,1992:847-854.
[3]
Barron A R.Approximation and estimation bounds for artificial neural networks[J].Machine Learning,1994,14:115-133.
[4]
Geman,Bienenstock,Doursat.Neural networks and the bias variance dilemma[J].Neural Computation,1992,4(1):1-58.
[5]
Castellano G,Fanilli A M,Pelillo M.A pruning algorithm for feed-forward neural networks[J].Neural Networks,1997,8(3):519-531.
[6]
Ponnapalli P V S.A formal selection and pruning algorithm for feed-forward artificial neural network optimization[J].Neural Networks,1999,10(4):964-968.
[7]
Kwok T Y,Yeung D Y.Constructive algorithm for structure learning in feed-forward neural networks for regression problems[J].Neural Networks,1997,8(3):630-645.
[8]
Lehtokangas M.Modified cascade-correlation learning for classification[J].Neural Networks,2000,11(3):795-798.
[9]
Hu T S,Lam K C,Thomas N G.River flow time series prediction with range-dependent neural network[J].Hydrological Sciences Journal,2001,46(5):729-745.
[10]
Perrone M P.General averaging results for convex optimization[C]//Proceedings of 1993 Connectionist Models Summer School,Hillsdale,1994:364-367.
[11]
Sietsma J,Dow R J F.Creating artificial neural networks that generation[J].Neural Networks,1991,4:67-79.
[12]
Maniezzo V.Genetic evolution of the topology and weight distribution of neural networks[J].Neural Networks,1994,5:39-53.
[13]
Fahlman S E,Lebiere C.The cascade connection learning architecture[C]//Advance in Neural Information Processing Systems,1990:524-532.
[14]
Amari S,Murata N,Muller K R.Asymptotic statistical theory of networks,over-training and cross-validation[J].Neural Networks,1997,8(5):985-996.
Kanaya F,Miyake S.Bayesian statistical behavior and valid generalization of pattern classifying neural networks[J].Neural Networks,1991,2(4):471-475.
[17]
Hartman.Training feedforward neural networks with gain constraints[J].Neural Computation,2000,12(4):811-829.
[18]
Deco.Unsupervised mutual information criterion for elimination of overtraining in supervised multilayer networks[J].Neural Computation,1994,7:1398-1419.
[19]
Ehrenfeucht A.A general lower bound on the number of examples needed for learning[C]//Proceedings of the Workshop on Computational Learning Theory,Morgan Kaufmann,1988.
[20]
Bishop C M.Neural Networks for Pattern Recognition[M].Oxford University Press,1995.
申金媛,刘玥,张文伟,等.利用汉明距离优选神经网络学习样本[J].光学学报,2000,20(9):1229-1233.Shen Jinyuan,Liu Yue,Zhang Wenwei,et al.Selecting of learning samples based on Hamming distance[J].Acta Optica Sinica,2000,20(9):1229-1233.
[23]
任俊玲.基于广义置信度的样本选择方法[J].中文信息学报,2007,21(3):106-109.Ren Junling.A pattern selection algorithm based on the generalized confidence[J].Journal of Chinese Information Processing,2007,21(3):106-109.
[24]
杨华波,张士峰,蔡洪.BP神经网络中定性信息的使用[J].计算技术与自动化,2005,24(3):15-17.Yang Huabo,Zhang Shifeng,Cai Hong.The using of qualitative information in BP neural networks[J].Computing Technology and Automation,2005,24(3):15-17.
[25]
陈祥光,薛锦诚,傅若农,等.引入模拟辅助样本提高BP网络的泛化能力[J].分析科学学报,2002,18(2):137-141.Chen Xiangguang,Xue Jincheng,Fu Ruonong,et al.Improvement of the generalization of BP networks with the aid of simulating assistant samples[J].Journal of Analytical Science,2002,18(2):137-141.
[26]
高学星,孙华刚,侯保林.使用不同置信级训练样本的神经网络学习方法[J].电子与信息学报,2014,36(6):1308-1311.Gao Xuexing,Sun Huagang,Hou Baolin.A neural network learning method using samples with different confidence levels[J].Journal of Electronics&Information Technology,2014,36(6):1308-1311.
[27]
Wang,Venkatesh.Optimal stopping and effective machine complexity in learning[J].NIPS6,CA,San Mat,1994:303-310.
[28]
Kearns M.A bound on the error of cross validation using the approximation and estimation rates with consequence for the training-test split[J].Neural Computation,1997,9:1143-1161.
[29]
Polycarpou M,Loannou P.Learning and convergence analysis of neural type structure networks[J].Neural Networks,1992,3:39-50.
胡铁松,沈佩君.前馈网络泛化性能改进的目的规划方法研究[J].系统工程学报,1997,12(2):34-39.Hu Tiesong,Shen Peijun.The goal programming method for improving generalization performance of the feedforward neural networks[J].Journal of System Engineering,1997,12(2):34-39.
[32]
Srecko Milanic,Stanko Strmcnik.Incorporating prior knowledge into artificial neural networks-an industrial case study[J].Neurocomputing,2004,62:131-151.
[33]
Hu T S,Lam K C,Thomas N G.A modified neural network for improving river flow prediction[J].Hydrological Sciences Journal,2005,50(2):299-318.
[34]
Jain,Srinivasulu.Integrated approach to modelling decomposed flow hydrograph using artificial neural network and conceptual techniques[J].Journal of Hydrology,2006,317(3-4):291-306.
[35]
Lloyd H C Chua,Tommy S W Wong.Runoff forecasting for an asphalt plane by artificial neural networks and comparisons with kinematic wave and autoregressive moving average models[J].Journal of Hydrology,2010,397:191-201.
[36]
Al-Mashouq K A.Including hints in training neural networks[J].Neural Computation,1991,3:418-427.
[37]
Abu-Mostafa Y S.Financial application of learning from hints[J].Ambridge,1995,MA:411-418.
[38]
Sill,Abu-MostafaY S.Advances in Neural Information Processing Systems[M].MIT Press,1997:643-640.
[39]
魏海坤,徐翤鑫,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.Wei Haikun,Xu Sixin,Song Wenzhong.Generalization theory and generalization methods for neural networks[J].Acta Automatic Sinica,2001,27(6):806-815.
[40]
陈翀伟,陈伟,陈德钊,等.基于先验知识的前馈网络对原油实沸点蒸馏曲线的仿真[J].高校化工学报,2001,15(4):351-356.Chen Chongwei,Chen Wei,Chen Dezhao,et al.Feedforward networks based on prior knowledge and its application in modeling the true boiling point curve of the crude oil[J].Journal of Chemical Engineering of Chinese Universities,2001,15(4):351-356.
[41]
Sanguesa,Cortes.Prior knowledge for learning networks in non-probabilistic settings[J].International Journal of Approximate Reasoning,2000,24:103-120.
[42]
Niyogo,Girosi.On the relationship between generalization error,hypothesis complexity,and sample complexity for radial basis function[J].Neural Computation,1996,8:819-842.
Zhao S Dillon.Incorporating prior knowledge in the form of production rules into neural networks using boolean-like neurons[J].Applied Intelligence,1997,7:275-285.
[51]
薛福珍,柏洁.基于先验知识和神经网络的非线性建模与预测控制[J].系统仿真学报,2004,(5):1057-1059.Xue Fuzhen,Bai Jie.Nonlinear modeling and predictive control based on prior knowledge and neural networks[J].Journal of System Simulation,2004,(5):1057-1059.
[52]
Fogel.An information criterion for optimal neural network selection[J].Neural Networks,1991,2(5):490-497.
[53]
Bartlett P L.For valid generalization:the size of the weight is more important than the size of the network[J].NIPS9,MA,Cambridge,1995:134-140.
[54]
Freund Y,Schapire R E.A decision-theoretic generalization of on-line learning and an application to boosting[J].Journal of Computer and System Sciences,1997,55(1):119-139.
[55]
Guan Donghai,Yuan Weiwei,Lee Youngkoo.Training data selection based on fuzzy c-means[C]//IEEE World Congress on Computational Intelligence,Hong Kong,2008:761-765.
[56]
Wang,Venkatesh.Temporal dynamics of generalization in neural networks[J].NIPS7,MA,Cambridge,1995:263-270.
[57]
Stork,Allen.How to solve the n-bit parity problem with two hidden units[J].Neural Networks,1992,5(6):923-926.
[58]
Federico Girosi,Nicholas Tung Chan.Prior knowledge and the creation of“Virtual”examples for RBF networks[C]//Neural Networks for Signal Processing,1995:201-210.
[59]
Barbar,Saad.Does extra knowledge necessarily improve generalization[J].Neural Computation,1996,8(1):202-214.
[60]
Psichogios D C,Ungar L H.SVD-Net:an algorithm that automatically selections network structure[J].Neural Networks,1994,5(3):513-515.
[61]
Baum E M,Haussler D.What size net gives valid generalization[J].JAMC,1989,36(4):929-965.
[62]
Kamimurar.Unification of information maximization and minimization[C]//Neural Information Processing Systems,1996:508-514.
[63]
Vapnik V N.The Nature of Statistical Learning Theory[M].New York:Springer Verlag,1995:1-20.
[64]
Mackay D J C.Information based objective function for active data selection[J].Neural Computation,1992,4:590-604.
[65]
何超,徐立新,张宇河.CMAC算法收敛性分析及泛化能力研究[J].控制与决策,2001,16(5):523-530.He Chao,Xu Lixin,Zhang Yuhe.Convergence and generalization ability of CMAC[J].Control and Decision,2001,16(5):523-530.
[66]
Holmstrom L,Koistinen P.Using additive noise in back propagation training[J].Neural Networks,1992,3(1):24-38.
[67]
An G.The effect of adding noise during back-propagation training on a generalization performance[J].Neural Computation,1996,8:643-671.
[68]
Hara K,Nakayama K Karaf.A training data selection in on-line training for multilayer neural networks[C]//IEEE World Congress on Computational Intelligence,1998,3:2247-2252.
[69]
顾正彬,李贺军,李克智,等.C/C复合材料等温CVI工艺模糊神经网络建模[J].稀有金属材料与工程,2004,33(10):1037-1040.Gu Zhengbin,Li Hejun,Li Kezhi,et al.Modeling of isothermal CVI process of C/C composites by fuzzy neural network[J].Rare Mental Materials and Engineering,2004,33(10):1037-1040.
[70]
Lincoln W L,Skrzypek J.Synergy of clustering multiple back-propagation networks[J].NIPS2,San Mateo,CA,1990:650-657.
[71]
Atiya A,Ji C.How initial condition affect generalization performance in large networks[J].Neural Networks,1997,8(2):448-451.
[72]
张海涛,陈宗海,向微,等.机理混合自适应时延神经网络建模和控制算法[J].系统仿真学报,2004,16(12):2709-2712.Zhang Haitao,Chen Zonghai,Xiang Wei,et al.An algorithm of modeling and control based on mechanism hybrid adaptive time delay neural network[J].Journal of System Simulation,2004,16(12):2709-2712.
[73]
Abu-Mostafa Y S.A method of learning from hints[J].NIPS,CA,1993:73-80.
[74]
Perantonis,Ampazis.Constrained learning in neural networks:Application to stable factorization of 2Dpolynomials[J].Neural Processing Letters,1998,(7):5-14.
[75]
YaochuJin,Bernhard Sendhoff.Knowledge incorporation into neural networks from fuzzy rules[J].Neural Processing Letters,1999,10(3):231-242.
[76]
李祚泳,易勇鸷.BP网络学习能力与泛化能力之间满足的定量关系式[J].电子学报,2003,31(9):1341-1344.Li Zuoyong,Yi Yongzhi.Quantitative relation between learning ability and generalization ability of BP neural network[J].Acta Electronic Sinica,2003,31(9):1341-1344.
Bo S.Optimal weight decay in perception[C]//Proceedings of the International Conference on Neural Networks,1996:551-556.
[79]
许少华,路阳,席海青,等.样本先验知识在神经网络训练中的应用[J].大庆石油学院学报,2004,28(6):66-69.Xu Shaohua,Lu Yang,Xi Haiqing,et al.Application of sample prior knowledge to nerve networks training[J].Journal of Daqing Petroleum Institute,2004,28(6):66-69.
[80]
Daniel T.Solving inverse problem by Bayesian neural network iterative inversion with ground truth incorporation[J].Signal Processing,1997,45(11):553-567.
[81]
Nowlan S J.Simplifying neural networks by soft weight sharing[J].Neural Computation,1992,4:473-493.
[82]
Jean,Wang.Weight smoothing to improve network generalization[J].Neural Networks,1994,5(5):752-763.
[83]
胡铁松.岩体爆破效应预测的前馈网络目的规划方法[J].水利学报,1997,(9):55-59.Hu Tiesong.The goal programming algorithm for feedforward neural network and its application to the prediction of rock mass blasting[J].Journal of Hydraulic Engineering,1997,(9):55-59.
[84]
陈立甲,伞冶,王子才,等.锅炉过热器系统机理与神经网络组合建模方法[J].中国电机工程学报,2001,21(1):73-76.Chen Lijia,San Ye,Wang Zicai,et al.A physical law and neural network integrated modeling method for bolier superheater systems[J].Proceedings of the CSEE,2001,21(1):73-76.
