Abstract
A Neural Network Ensemble (NNE) combines the outputs of several individually trained neural networks in order to improve generalization performance. This article summarizes different approaches on the development and the latest studies on NNE. The introduction of the basic principles of NNE is followed by detailed descriptions of individual neural network generation method, conclusion generation method and fusion based on granular computing and NNE. In addition, for each of these methods we provide a short taxonomy in terms of their relevant characteristics, and analyze several of NNE applications, classic algorithms and contributions on various fields.
Similar content being viewed by others
References
Abbass HA (2000) A memetic pareto evolutionary approach to artificial neural networks. In: Proceedings of the 14th Australian joint conference on artificial intelligence. Springer, Berlin, pp 1–12
Abraham A, Grosan C, Han S, Gelbukh A (2005) Evolutionary multiobjective optimization approach for evolving ensemble of intelligent paradigms for stock modeling. In: Lecture notes in computer science. pp 673–681
Alhamdoosh M, Wang D (2014) Fast decorrelated neural network ensembles with random weights. Inf Sci 264:104–117
Ao SI, Palade V (2011) Ensemble of Elman neural networks and support vector machines for reverse engineering of gene regulatory networks. Appl Soft Comput 11(2):1718–1726
Bakker B, Heskes T (2003) Clustering ensembles of neural network models. Neural Netw 16:261–269
Baumgartner D, Serpen G (2013) Performance of global-local hybrid ensemble versus boosting and bagging ensembles. Int J Mach Learn Cybern 4(4):301–317
Benediktsson JA, Sveinsson JR, Ersoy OK, Swain PH (1997) Parallel consensual neural networks. IEEE Trans Neural Netw 8(1):54–64
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140
Breiman L (2000) Randomizing outputs to increase prediction accuracy. Mach Learn 40(3):229–242
Brown G (2004) Diversity in neural network ensembles. Ph.D. dissertation of University of Birmingham
Brown G, Wyatt J, Harris R, Yao X (2005) Diversity creation methods: a survey and categorization. Inf Fusion 6(1):5–20
Calderon D, Baidyk T, Kussul E (2013) Hebbian ensemble neural network for robot movement control. Opt Mem Neural Netw 22(3):166–183
Chandra A, Yao X (2004) DIVACE: diverse and accurate ensemble learning algorithm. In: Lecture notes in computer science. pp 619–625
Chen GC, Yu JS (2005) Particle swarm optimization neural network and its application in soft-sensing modeling. In: Lecture notes in computer science, vol 3611. pp 610–617
Chen H, Yuan S, Jiang K (2005) Wrapper approach for learning neural network ensemble by feature selection. In: Lecture notes in computer science. pp 526–531
Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20(3):273–297
Cunningham P , Carney J (2000) Diversity versus quality in classification ensembles based on feature selection. In: European conference on machine learning. Springer, Berlin, pp 109–116
Dai K, Zhao J, Cao F (2015) A novel decorrelated neural network ensemble algorithm for face recognition. Knowl Based Syst 89:541–552
Dietterich TG (1998) Machine-learning research: four current directions. Al Mag 18(4):97–136
Dietterich TG, Bakiri G (1991) Error-correcting output codes: a general method for improving multiclass inductive learning Programs. In: Proceedings of the ninth AAAI national conference on artificial intelligence, AAAI Press, Menlo Park, CA, pp 572–577
Ding S, Li H (2014) Quotient space granularity selection based affinity propagation clustering algorithm. J Comput Inf Syst 10(6):2425–2433
Ding S, Li H (2015) Twice clustering based individual neural network generation method. Neurocomputing 157:264–272
Ding S, Jia H, Chen J, Jin F (2014) Granular neural networks. Artif Intell Rev 41(3):373–384
Dong J, Zheng C, Kan G, Zhao M, Wen J, Yu J (2015) Applying the ensemble artificial neural network-based hybrid data-driven model to daily total load forecasting. Neural Comput Appl 26:603–611
Duin RPW, Tax DMJ (2000) Experiments with classifier combining rules. In: Proceedings of the international workshop on multiple classifier systems, Calgiari. Springer, Italy, pp 16–19
Eysa S, Saeed G (2005) Optimum design of structures by an improved genetic algorithm using neural networks. Adv Eng Softw 36(11):757–767
Faußer S, Schwenker F (2015) Neural network ensembles in reinforcement learning. Neural Process Lett 41:55–69
Fernández C, Valle C, Saravia F, Allende H (2012) Behavior analysis of neural network ensemble algorithm on a virtual machine cluster. Neural Comput Appl 21:535–542
Freund Y (1995) Boosting a weak algorithm by majority. Inf Comput 121(2):256–285
Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139
Fu X, Feng B, Ma Z, He M (2004) Method of incremental construction of heterogeneous neural network ensemble with negative correlation. J Xi’an Jiaotong Univ 38(8):796–799
Fu Q, Hu SX, Zhao SY (2005) Clustering-based selective neural network ensembles. J Zhejiang Univ Sci 6A(5):387–392
Gao H, Gao L, Zhou C, Yu D (2004) Particle swarm optimization based algorithm for neural network learning. Chin J Electron 32(9):1572–1574
Garcia-Pedrajas N, Hervas-martinez C, Ortiz-boyer D (2005) Cooperative coevolution of artificial neural network ensembles for pattern classification. IEEE Trans Evol Comput 9(3): 271–302
Ghazikhani A, Monsefi R, Yazdi HS (2013) Ensemble of online neural networks for non-stationary and imbalanced data streams. Neurocomputing 122:535–544
Giacinto G, Roli F (2001) An approach to the automatic design of multiple classifier systems. Pattern Recognit Lett 22:25–33
Gutta S, Wechsler H (1997) Face recognition using hybrid classifiers. Pattern Recognit 30(4):539–553
Gutta S, Huang JRJ, Jonathon P, Wechsler H (2000) Mixture of experts for classification of gender, ethnic origin, and pose of human faces. IEEE Trans Neural Netw 11(4):948–960
Hadavandi E, Shahrabi J, Shamshirband S (2015) A novel boosted-neural network ensemble for modeling multi-target regression problems. Eng Appl Artif Intell 45:204–219
Han M, Zhu X, Yao W (2012) Remote sensing image classification based on neural network ensemble algorithm. Neurocomputing 78(1):133–138
Hang C, Gao J (2010) Fast license plate character recognition based on AdaBoost. Comput Mod 9:140–143
Hansen LK, Salamon P (1990) Neural network ensembles. IEEE Trans Pattern Anal Mach Intell 12(10):993–1001
Hansen LK, Salamon P (1992) Ensemble methods for handwritten digit recognition. In: Proceeding of IEEE workshop on neural networks for signal processing, Copenhagen, Denmark, pp 333–342
Hayashi Y, Setiono R (2002) Combining neural network predictions for medical diagnosis. Comput Biol Med 32:237–246
Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 20(8):832–844
Islam MM, Yao X, Murase K (2003) A constructive algorithm for training cooperative neural network ensembles. IEEE Trans Neural Netw 14(4):820–834
Jang M, Cho S (2002) Observational learning algorithm for an ensemble of neural networks. Pattern Anal Appl 5(2):154–167
Kanal L (1974) Patterns in pattern recognition. IEEE Trans Inf Theory (IT–20):697–722
Khare V, Yao X (2002) Artificial speciation of neural network ensembles. In: Proceedings of the 2002 UK workshop on computational intelligence (UKCI’02), University of Birmingham, UK, pp 96–103
Kokkinos Y, Margaritis KG (2014) A distributed privacy-preserving regularization network committee machine of isolated peer classifiers for P2P data mining. Artif Intell Rev 42:385–402
Kokkinos Y, Margaritis KG (2015) Confidence ratio affinity propagation in ensemble selection of neural network classifiers for distributed privacy-preserving data mining. Neurocomputing 150:513–528
Kourentzes N, Barrow DK, Crone SF (2014) Neural network ensemble operators for time series forecasting. Expert Syst Appl 41(9):4235–4244
Krawczyk B (2015) Forming ensembles of soft one-class classifiers with weighted bagging. New Gener Comput 33:449–466
Krogh A, Vedelsby J (1995) Neural network ensembles, cross validation, and active learning. In: Advances in neural information processing systems 7, Denver, CO: MIT Press, Cambridge, MA, pp 231–238
Langdon WB, Barrett SJ, Buxton BF (2002) Combining decision trees and neural networks for drug discovery. In: Proceedings of the 5th european conference on genetic programming, Kinsale, Ireland, pp 60–70
Lazarevic A, Obradovic Z (2001) Effective pruning of neural network classifier ensembles. In: Proceedings of the international joint conference on neural networks, pp 796–801
Lee H, Kim E, Pedrycz W (2012) A new selective neural network ensemble with negative correlation. Appl Intell 37:488–498
Lee H et al (2014) A New gait recognition system based on hierarchical fair competition-based parallel genetic algorithm and selective neural network ensemble. Int J Control Autom Syst 12(1):202–207
Li H, Ding S (2013a) A novel neural network classification model based on covering and affinity propagation clustering algorithm. J Comput Inf Syst 9(7):2565–2573
Li H, Ding S (2013b) Research and development of granular neural networks. Appl Math Inf Sci 7(3):1251–1261
Li H, Ding S (2013c) Research of individual neural network generation and ensemble algorithm based on quotient space granularity clustering. Appl Math Inf Sci 7(2):701–708
Li K, Huang H (2005a) A selective approach to neural network ensemble based on clustering technology. J Comput Res Dev 42(4):594–598
Li K, Huang H (2005b) An approach to improving diversity of neural network ensemble. Acta Electron Sin 33(8):1387–1390
Li J, Peng M (2005) GDP forecasting model based on neural networks ensemble. Chin J Manag 4:434–436
Li G, Yang J, Kong A, Chen N (2004) Clustering algorithm based selective ensemble. J Fudan Univ (Nat Sci) 43(5):689–692
Li L, Liu X, Lu S (2007) Constructive methods for parallel learning neural network ensemble based on particle swarm optimization. ShanDong Sci 20(4):16–20
Liao Y, Moody J (1999) Constructing heterogeneous committees using input feature grouping. Adv Neural Inf Process Syst 12:921–927
Liew WS, Seera M, Loo CK (2015) Hierarchical parallel genetic optimization fuzzy ARTMAP ensemble. Neural Process Lett. doi:10.1007/s11063-015-9467-9
Lin J, Peng M (2005) GDP forecasting model based on neural networks ensemble. Chin J Manag 2(4):434–436
Lin J, Zhu B (2005) Neural network ensemble based on forecasting effective measure and its application. J Comput Inf Syst 1(4):781–787
Ling J, Zhou Z (2004) Causal discovery based on neural network ensemble method. J Softw 15(10):1479–1484
Ling J, Chen Z, Zhou Z (2004) Feature selection based neural network ensemble method. J Fudan Univ (Nat Sci) 43(5):685–688
Liu Y (1998) Negative correlation learning and evolutionary neural network ensembles. The University of New South Wales, Australian Defence Force Academy, Canberra, Australia
Liu Y, Yao X (1998) Negatively correlated neural networks for classification. In: Proceedings of the third international symposium on artificial life and robotics (AROBlll, 98), Beppu, Japan, pp 736–739
Liu Y, Yao X (1999a) Simultaneous training of negatively correlated neural networks in an ensemble. IEEE Trans Syst Man Cybern B Cybern 29(6):716–725
Liu Y, Yao X (1999b) Ensemble learning via negative correlation. Neural Netw 12:1399–1404
Liu Y, Yao X (2002) Learning and evolution by minimization of mutual information. In: Lecture notes in computer science, pp 495–504
Liu Y, Yao X, Higuchi T (2000) Evolutionary ensembles with negative correlation learning. IEEE Trans Evol Comput 4(4):380–387
Liu H, Chen G, Song G et al (2010) AdaBoost based ensemble of neural networks in analog circuit fault diagnosis. Chin J Sci Instrum 4:851–856
Loo CK, Liew WS, Seera M, Lim E (2015) Probabilistic ensemble fuzzy ARTMAP optimization using hierarchical parallel genetic algorithms. Neural Comput Appl 26(2):263–276
Luiz O, Morita M, Sabourin R (2006) Feature selection for ensembles using the multi-objective optimization approach. In: Studies in computational intelligence, vol 16, pp 49–74
Lu J, Zhang W (2002) Design for Chinese text classier. Comput Eng Appl 15:49–51
Lysiak R, Kurzynski M, Woloszynski T (2014) Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers. Neurocomputing 126:29–35
Maclin R, Shavlik JW (1995) Combining the predictions of multiple classifiers: using competitive learning to initialize neural networks. In: Proceedings of the 14th international joint conference on artificial intelligence, Montreal, Canada, pp 524–530
Mao J, Mohiuddin KM (1997) Improving OCR performance using character degradation models and boosting algorithm. Pattern Recognit Lett 18(11–13):1415–1419
Masoudnia S, Ebrahimpour R (2014) Mixture of experts: a literature survey. Artif Intell Rev 42(2):275–293
Mckay R, Abbass H (2011a) Analyzing anticorrelation in ensemble learning. In: Proceedings of 2001 conference on artifficial neural networks and expert systems, Otago, New Zealand, pp 22–27
Mckay R, Abbass H (2011b) Anticorrelation measures in genetic programming. In: Australasia–Japan workshop on intelligent and evolutionary systems, pp 45–51
Melville P, Mooney R (2003) Constructing diverse classifier ensembles using artificial training examples. In: Proceedings of the eighteenth international joint conference on artificial intelligence, Mexico, pp 505–510
Melville P, Mooney RJ (2005) Creating diversity in ensembles using artificial data. Inf Fusion 6:99–111
Mendes-Moreira J, Soares C, Jorge AM, de Sousa JF (2012) Ensemble approaches for regression: a survey. ACM Comput Surv 45(1), Article 10, p 40
Meng J, Wang Y, Wang T, Gong D (2005) Immune learning algorithm based on neural network ensemble. J China Univ Ming Technol 34(4):486–489
Minsky M (1991) Logical versus analogical or symbolic versus connectionist or neat versus scruffy. Al Mag 12:34–51
Navone HD, Verdes PF, Granitto PM, Ceccatto HA (2000) Selecting diverse members of neural network ensemble. In: Proceedings of the 6th Brazilian symposium on neural networks, pp 255–260
Nilsson NJ (1965) Learning machines: foundations of trainable pattern-classifying. McGraw Hill, New York
Oliveira LS, Sabourin R, Bortolozzi F, Suen CY (2003) A methodology for feature selection using multi-objective genetic algorithm for handwritten digit string recognition. Int J Pattern Recognit Artif Intell 17(6):903–930
Opitz D (1999) Feature selection for ensembles. In: Proceedings of 16th national conference on artificial intelligence (AAAI), pp 379–384
Opitz DW, Shavlik JW (1996a) Generating accurate and diverse members of a neural network ensemble. In: Advances in neural information processing systems 8, Denver, CO: MIT Press, Cambridge, MA, pp 535–541
Opitz DW, Shavlik JW (1996b) Actively searching for an effective neural network ensemble. Connect Sci 8(3–4):337–353
Oza NC, Tumer K (2001) Input decimation ensembles: decorrelation through dimensionality reduction. In: Proceedings of the international workshop on multiple classifier systems, Cambridge, UK, Springer, pp 238–247
Parmanto B, Munro PW, Doyle HR (1996) Improving committee diagnosis with resampling techniques. Adv Neural Inf Process Syst 8:882–888
Partridge D (1996) Network generalization differences quantified. Neural Netw 9(2):263–271
Partridge D, Yates WB (1996) Engineering multiversion neural network systems. Neural Comput 8(4):869–893
Pawlak Z (1982) Rough sets. Int J Comput Inf Sci 11:341–356
Pedrycz W (2001) Granular computing: an emerging paradigm. IEEE Trans Syst Man Cybernet 32(2):212–224
Perrone MP, Cooper LN (1993) When networks disagree: ensemble method for neural networks. Artif Neural Netw Speech Vision 12(10):126–142
Pitoyo H, Shuji H (2002) Adaptive neural network ensemble that learns from imperfect supervisor. In: Proceedings of the 9th International conference on neural information processing (ICONIP02), vol 5, pp 2561–2565
Pulido M, Melin P, Castillo O (2014) Particle swarm optimization of ensemble neural networks with fuzzy aggregation for time series prediction of the Mexican Stock Exchange. Inf Sci 280(1):188–204
Qian B, Li Y, Tang Z (2008) Speaker recognition algorithm based on neural network ensemble and its simulation study. J Syst Simul 5:1285–1288
Qin Z, Liu Y, Heng X, Wang X (2005) Negatively correlated neural network ensemble with multi-population particle swarm optimization. In: Lecture notes in computer science, pp 520–525
Raviv Y, Intrator N (1996) Bootstrapping with noise: an effective regularization technique. Connect Sci 8:355–372
Rokach L (2010) Ensemble-based classifiers. Artif Intell Rev 33:1–39
Roli F, Giacinto G, Vernazza G (2001) Methods for designing multiple classifier systems. In: Kittler J, Roli F (eds) MCS2001, Lecture notes in computer science. Springer, Beilin, pp 78–87
Rosen BE (1996) Ensemble learning using decorrelated neural networks. Connect Sci Spec Issue Comb Artif Neural Netw Ensemble Approach 8(3&4):373–384
Schapire RE (1990) The strength of weak learnability. Mach Learn 5(2):197–227
Schapire RE, Freund Y, Bartlett Y, Lee WS (1998) Boosting the margin: a new explanation for the efectiveness of voting methods. Ann Stat 26(5):1651–1686
Schwenk H, Bengio Y (1997) Adaptive boosting of neural network for character recognition. Technical report, University de Montreal
Sesmero MP, Alonso-Weber JM, Gutiérrez G, Ledezma A, Sanchis A (2012) A new artificial neural network ensemble based on feature selection and class recoding. Neural Comput Appl 21(4):771–783
Sharkey N, Neary J, Sharkey A (1995) Searching weight space for back propagation solution types. In: Current trends in connectionism: Proceedings of the 1995 Swedish conference on connectionism, pp 103–120
Shen X, Zhou Z, Wu J, Chen Z (2000) Survey of boosting and bagging. Comput Eng Appl 12:31–33
Shi Y, Huang C, Hou C (2004) Two-level ensemble of selective neural network based on stochastic gradient. Comput Eng 30(16):133–135
Shi Y, Huang C, Hou C (2005) The study of the two-level selective neural network ensembles modeling for quantity structure-activity relationship (QSAR). Comput Appl Chem 22(2):153–156
Shimshoni Y, Intrator N (1998) Classification of seismic signals by integrating ensembles of neural networks. IEEE Trans Signal Process 46(S):1194–1201
Smith C, Jin Y (2014) Evolutionary multi-objective generation of recurrent neural network ensembles for time series prediction. Neurocomputing 143:302–311
Soares SG, Araújo R (2015) An on-line weighted ensemble of regressor models to handle concept drifts. Eng Appl Artif Intell 37:392–406
Soares SG, Antunes CH, Araújo R (2013) Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development. Neurocomputing 121:498–511
Sollich P, Krogh A (1996) Learning with ensembles: how over-fitting can be useful. In: Advances in neural information processing systems, Denver, CO: MIT Press, Cambridge, MA, pp 190–196
Song X, Xia L (2004) Intelligent regulation of reservoir based on bagging algorithm. Comput Eng Appl 25:218–219
Sun B, Gong N, Zhu W (2006) Application of neural network ensemble based on covering algorithm in speech recognition. J Nanjing Univ (Natural Sciences) 3:331–336
Tang C, Gao X (2001) The researching development of evolutionary neural networks. J Syst Eng Electron 23(10):92–97
Tian J, Li M, Chen F, Kou J (2012) Coevolutionary learning of neural network ensemble for complex classification tasks. Pattern Recognition 45(4):1373–1385
Tran TP, Nguyen TTS, Tsai P, Kong X (2011) BSPNN: boosted subspace probabilistic neural network for email security. Artif Intell Rev 35(4):369–382
Tsymbal A, Pechenizkiy M, Cunningham P (2005) Diversity in search strategies for ensemble feature selection. Inf Fusion 6:83–98
Valle C, Saravia F, Allende H, Monge R, Fernández C (2010) Parallel approach for ensemble learning with locally coupled neural networks. Neural Process Lett 32(3):277–291
Verma B, Hassan SZ (2011) Hybrid ensemble approach for classification. Appl Intell 34(2):258–278
Wang Q, Wen B (2009) High frequency ground wave radar sea clutter predicting based on artificial neural network selection and ensembling. Syst Eng Electron 12:2801–2805
Wang W, Jones P, Partridge D (2000) Diversity between neural networks and decision trees for building multiple classier systems. In: Proceedings of the international workshop on multiple classier systems, Springer, Calgiari, Italy, pp 240–249
Wang Z-Q, Chen S-F, Chen Z-Q, Xie J-Y (2004) A parallel learning approach for neural network ensemble. In: AI 2004, advances in artificial intelligence, lecture notes in computer science 3339, pp 1200–1205
Wang Z, Chen S, Chen Z (2005) An active learning approach for neural network ensemble. J Comput Res Dev 42(3):375–380
Woods K, Kegelmeyer W, Bowyer K (1997) Combination of multiple classiers using local accuracy estimates. IEEE Trans Pattern Anal Mach Intell 19:405–410
Wozniak M, Graña M, Corchado E (2014) A survey of multiple classifier systems as hybrid systems. Inf Fusion 16:3–17
Wu J, Zhihua Z, Zhaoqian C (2001) Ensemble of GA-based selective neural network ensembles. In: Proceedings of the 8th international conference on neural information processing (ICONIP’01), Shanghai, China, pp 1477–1482
Xin Y (2001) Neural network ensembles and their application to traffic flow prediction in telecommunications networks. IEEE Trans Evol Comp 4:693–698
Xing J, Xiao D (2007) CSTR state estimate based on neural network ensemble. Comput Appl Chem 4:433–436
Xu H, Wang S, Wang R et al (2010) Research of P2P traffic identification based on neural network ensemble. J Nanjing Univ Posts Telecommun (Nat Sci) 3:79–83
Yang T, Zhang C (2008) Freeway incident detection based on Adaboost RBF neural network. Comput Eng Appl 32:223–225
Yang J, Zeng X, Zhong S, Wu S (2013) Effective neural network ensemble approach for improving generalization performance. IEEE Trans Neural Netw Learn Syst 24(6):878–887
Yao YY (2000) Granular computing: basic issues and possible solutions. In: Wang PP (ed) Proceedings of the 5th joint conference on information sciences. Association for Intelligent Machinery Press, Atlantic City, pp 186–189
Yao X, Liu Y (1998) Making use of population information in evolutionary artificial neural networks. IEEE Trans Syst Man Cybernet B Cybernet 28(3):417–425
Yao W, Wang Q, Chen Z, Wang J (2004) The researching overview of evolutionary neural network. Comput Sci 31(3):125–129
Yaochu J, Okabe T, Sendhoff B (2004) Neural network regularization and ensembling using multi-objective evolutionary algorithms. In: Congress on evolutionary computation, pp 1–81
Yates W, Partridge D (1996) Use of method ological diversity to improve neural network generalization. Neural Comput Appl 4(2):114–128
Yin XC, Huang K, Yang C, Hao HW (2014) Convex ensemble learning with sparsity and diversity. Inf Fusion 20:49–59
Yong L, Xin Y (1998) A cooperative ensemble learning system. In: IEEE world congress on computational intelligence. The 1998 IEEE international joint conference on neural networks proceedings, pp 2202–2207
Yong L, Xin Y, Qiangfu Z, Higuchi T (2001) Evolving a cooperative population of neural networks by minimizing mutual information. In: Proceedings of the 2001 congress on evolutionary computation, pp 384–389
Yu F, Liu H, Tan G (2007) Application of neural network ensemble for structural damage detection. J Jilin Univ (Engineering and Technology Edition) 2:438–441
Yu J (2011) Online tool wear prediction in drilling operations using selective artificial neural network ensemble model. Neural Comput Appl 20(4):473–485
Zadeh LA (1996) Fuzzy logic = computing with words. IEEE Trans Fuzzy Syst 2:103
Zenobi G, Cunningham P (2001) Using diversity in preparing ensembles of classifiers based on different feature subsets to minimize generalization error. In: Lecture Notes in Computer Science 2169, pp 576–587
Zhang GP (2000) Neural Networks for classification: a survey. IEEE Trans Syst Man Cybernet C Appl Rev 30(4):451–462
Zhang X, Xu L (2003) The stock market forecast model based on neural network ensemble. Syst Eng Theory Pract 9:67–70
Zhang L, Zhang B (2003) Theory of fuzzy quotient space: methods of fuzzy granular computing. J Softw 14(4):770
Zhang Y, Zhong S (2013) A privacy-preserving algorithm for distributed training of neural network ensembles. Neural Comput Appl 22:S269–S282
Zhao Z-S, Feng X, Lin Y-Y, Wei F, Wang S-K, Xiao T-L, Cao M-Y, Hou Z-G (2015) Evolved neural network ensemble by multiple heterogeneous swarm intelligence. Neurocomputing 49:29–38
Zhang YQ, Fraser MD, Gagliano RA, Kandel A (2000) Granular neural networks for numerical-linguistic data fusion and knowledge discovery. IEEE Trans Neural Netw 11(3):658–667
Zheng J, Liu Y, Liu Q, Sun M (2004) A dynamic integration approach for a neural network ensemble. Comput Eng 30(03):49–50
Zhou Z, Huang F, Zhang H (2001) View-invariant face recognition based on neural network ensemble. J Comput Res Dev 10:1204–1210
Zhou Z, Wu J, Tang W (2002) Ensembling neural networks: many could be better than all. Artifi Intell 137(2):239–263
Zhu Q, Meng Q (2009) A new selective neural network ensemble method and its application in purified terephthalic acid solvent system. CIESC J 10:2510–2516
Acknowledgements
This work is supported by the National Natural Science Foundation of China (No.61379101), the National Key Basic Research Program of China (No.2013CB329502), the Natural Science Foundation of Jiangsu Normal University (No. 14XLA12), National Natural Science Foundation of China (No. 61472424) and Fundamental Research Funds for the Central Universities under Grant 2013RC10.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, H., Wang, X. & Ding, S. Research and development of neural network ensembles: a survey. Artif Intell Rev 49, 455–479 (2018). https://doi.org/10.1007/s10462-016-9535-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-016-9535-1