메뉴 건너뛰기




Volumn 3, Issue 3, 2013, Pages 105-115

Pruning algorithms of neural networks - A comparative study

Author keywords

classification; data mining; feedforward neural networks; input and hidden neurons pruning; optimization techniques

Indexed keywords

CLASSIFICATION (OF INFORMATION); DATA MINING; FEEDFORWARD NEURAL NETWORKS; SENSITIVITY ANALYSIS;

EID: 84908620612     PISSN: None     EISSN: 22991093     Source Type: Journal    
DOI: 10.2478/s13537-013-0109-x     Document Type: Article
Times cited : (117)

References (46)
  • 2
    • 84858776353 scopus 로고    scopus 로고
    • A new pruning algorithm for feedforward neural networks
    • IEEE Conference Publication, Wuhan, Hubei, China 19-21 October
    • A. Fangju, A New Pruning Algorithm for Feedforward Neural Networks, Fourth International Workshop on Advanced Computational Intelligence, IEEE Conference Publication, Wuhan, Hubei, China 19-21 October 2011, 286-289
    • (2011) Fourth International Workshop on Advanced Computational Intelligence , pp. 286-289
    • Fangju, A.1
  • 4
    • 51549113917 scopus 로고    scopus 로고
    • A novel algorithm for designing three layered artificial neural networks
    • S. Ahmmed, K. Abdullah-Al-Mamun, M. Islam, A novel algorithm for designing three layered artificial neural networks, Int. J. Soft. Comput. 2 (3), 450-458, 2007
    • (2007) Int. J. Soft. Comput , vol.2 , Issue.3 , pp. 450-458
    • Ahmmed, S.1    Abdullah-Al-Mamun, K.2    Islam, M.3
  • 5
    • 65249163364 scopus 로고    scopus 로고
    • An incremental framework based on cross validation for estimating the architecture of a multilayer perceptron
    • O. Aran, O. T. Yildiz, E. Alpaydin, An incremental framework based on cross validation for estimating the architecture of a multilayer perceptron, Int. J. Pttern. Recogn. Artif. Intell. 23 (2), 159-190, 2009
    • (2009) Int. J. Pttern. Recogn. Artif. Intell , vol.23 , Issue.2 , pp. 159-190
    • Aran, O.1    Yildiz, O.T.2    Alpaydin, E.3
  • 6
    • 33750378348 scopus 로고    scopus 로고
    • A new training and pruning algorithm based on node dependence and Jacobian rank deficiency
    • J. Xua, D. W. C. Hob, A new training and pruning algorithm based on node dependence and Jacobian rank deficiency, Neurocomputing 70, 544-558, 2006
    • (2006) Neurocomputing , vol.70 , pp. 544-558
    • Xua, J.1    Hob, D.W.C.2
  • 7
    • 56549091450 scopus 로고    scopus 로고
    • Solving local minima problem with large number of hidden nodes on two layered feedforward artificial neural networks
    • B. Choi, J. HongLee, D.-H. Kim, Solving local minima problem with large number of hidden nodes on two layered feedforward artificial neural networks, Neurocomputing 71, 3640-3643, 2008
    • (2008) Neurocomputing , vol.71 , pp. 3640-3643
    • Choi, B.1    Lee, J.H.2    Kim, D.-H.3
  • 9
    • 0027662338 scopus 로고
    • Pruning algorithms a survey
    • R. Reed, Pruning algorithms a survey, IEEE T. Neural Networ. 4 (5), 740-747, 1993
    • (1993) IEEE T. Neural Networ , vol.4 , Issue.5 , pp. 740-747
    • Reed, R.1
  • 11
    • 0027668417 scopus 로고
    • Determining and improving the fault tolerance of multi layer perceptrons in a pattern-recognition application
    • M. D. Emmerson, R. I. Damper, Determining and improving the fault tolerance of multi layer perceptrons in a pattern-recognition application, IEEE T. Neural Networ. 4, 788-793, 1993
    • (1993) IEEE T. Neural Networ , vol.4 , pp. 788-793
    • Emmerson, M.D.1    Damper, R.I.2
  • 13
    • 50849098868 scopus 로고    scopus 로고
    • A note on knowledge discovery using neural networks and its application to credit card screening
    • R. Setiono, B. Baesens, C. Mues, A note on knowledge discovery using neural networks and its application to credit card screening, Eur. J. Oper. Res. 192 (1), 326-332, 2008
    • (2008) Eur. J. Oper. Res , vol.192 , Issue.1 , pp. 326-332
    • Setiono, R.1    Baesens, B.2    Mues, C.3
  • 14
    • 84861794233 scopus 로고    scopus 로고
    • Reverse engineering the neural networks for rule extraction in classification problems
    • M. G. Augasta, T. Kathirvalavakumar, Reverse Engineering the Neural Networks for Rule Extraction in Classification Problems, Neural Process. Lett. 35, 131-150, 2012
    • (2012) Neural Process. Lett , vol.35 , pp. 131-150
    • Augasta, M.G.1    Kathirvalavakumar, T.2
  • 15
    • 0035505658 scopus 로고    scopus 로고
    • A new pruning heuristic based on variance analysis of sensitivity information
    • A. P. Engelbrecht, A new pruning heuristic based on variance analysis of sensitivity information, IEEE T. Neural Networ. 12 (6), 1386-1399, 2001
    • (2001) IEEE T. Neural Networ , vol.12 , Issue.6 , pp. 1386-1399
    • Engelbrecht, A.P.1
  • 16
    • 33745937122 scopus 로고    scopus 로고
    • Effective neural network pruning using cross validation
    • Montreal, 31 July-4 August
    • T. Q. Huynh, R. Setiono, Effective neural network pruning using cross validation, In: Proc. of IEEE Int. Joint Conference on Neural Networks 2, Montreal, 31 July-4 August 2005, 972-977
    • (2005) Proc. of IEEE Int. Joint Conference on Neural Networks , vol.2 , pp. 972-977
    • Huynh, T.Q.1    Setiono, R.2
  • 17
    • 0031142667 scopus 로고    scopus 로고
    • An Iterative Pruning algoritm for feedforward neural networks
    • G. Castellano, A. M. Fanelli, M. Pelillo, An Iterative Pruning algoritm for feedforward neural networks, IEEE T Neural Networ. 8 (3), 519-530, 1997
    • (1997) IEEE T Neural Networ , vol.8 , Issue.3 , pp. 519-530
    • Castellano, G.1    Fanelli, A.M.2    Pelillo, M.3
  • 18
    • 0036789790 scopus 로고    scopus 로고
    • A self organizing network that grows when required
    • S. Marsland, S. U. Nehmzow, J. Shapiro, A self organizing network that grows when required, Neural Networ. 15 (809), 1041-1058, 2002
    • (2002) Neural Networ , vol.15 , Issue.809 , pp. 1041-1058
    • Marsland, S.1    Nehmzow, S.U.2    Shapiro, J.3
  • 19
    • 84867839878 scopus 로고    scopus 로고
    • Universal approximation of extreme learning machine with adaptive growth of hidden nodes
    • R. Zhang, Y. Lan, G. B. Huang, Z. B. Xu, Universal approximation of extreme learning machine with adaptive growth of hidden nodes, IEEE T. Neural Networ. Learn. Syst. 23 (2), 365-371, 2012
    • (2012) IEEE T. Neural Networ. Learn. Syst , vol.23 , Issue.2 , pp. 365-371
    • Zhang, R.1    Lan, Y.2    Huang, G.B.3    Xu, Z.B.4
  • 20
    • 56549090053 scopus 로고    scopus 로고
    • 20. Enhanced random search based incremental extreme learning machine
    • G. B. Huang, L. Chen, 20. Enhanced random search based incremental extreme learning machine, Neuro Comput. 71 (16-18), 3460-3468, 2008
    • (2008) Neuro Comput , vol.71 , Issue.16-18 , pp. 3460-3468
    • Huang, G.B.1    Chen, L.2
  • 21
    • 44649169676 scopus 로고    scopus 로고
    • Structure learning by pruning in independent component analysis
    • A. B. Nielsen, L. K. Hansen, Structure learning by pruning in independent component analysis, Neuro Comput. 71 (10-12), 2281-2290, 2008
    • (2008) Neuro Comput , vol.71 , Issue.10-12 , pp. 2281-2290
    • Nielsen, A.B.1    Hansen, L.K.2
  • 23
    • 0025792215 scopus 로고
    • Bounds on the number of hidden neurons in multilayer perceptrons
    • S. C. Huang, Y. F. Huang, Bounds on the number of hidden neurons in multilayer perceptrons, IEEE T. Neural Networ. 2, 47-55, 1991
    • (1991) IEEE T. Neural Networ , vol.2 , pp. 47-55
    • Huang, S.C.1    Huang, Y.F.2
  • 24
    • 84867891849 scopus 로고    scopus 로고
    • A structure optimisation algorithm for feedforward neuralnetwork construction
    • H.-G. Han, J.-F. Qiao, A structure optimisation algorithm for feedforward neuralnetwork construction, Neurocomputing 99, 347-357, 2013
    • (2013) Neurocomputing , vol.99 , pp. 347-357
    • Han, H.-G.1    Qiao, J.-F.2
  • 26
    • 44649169676 scopus 로고    scopus 로고
    • Structure learning by pruning in independent component analysis
    • A. B. Nielsen, L. K. Hansen, Structure learning by pruning in independent component analysis, Neurocomputing, 71 (10-12), 2281-2290, 2008
    • (2008) Neurocomputing , vol.71 , Issue.10-12 , pp. 2281-2290
    • Nielsen, A.B.1    Hansen, L.K.2
  • 28
    • 54449083953 scopus 로고    scopus 로고
    • Fast unit pruning algorithm for feed-forward neural network design
    • Q. Jun-fei, Z. Ying, H. Hong-gui, Fast unit pruning algorithm for feed-forward neural network design, App. Math. Comput. 205 (2), 662-667, 2008
    • (2008) App. Math. Comput , vol.205 , Issue.2 , pp. 662-667
    • Jun-Fei, Q.1    Ying, Z.2    Hong-Gui, H.3
  • 30
    • 0030633575 scopus 로고    scopus 로고
    • A penalty function approach for pruning feedforward neural networks
    • R. Setiono, A penalty function approach for pruning feedforward neural networks, Neural Comput. 9 (1), 185-204, 1997
    • (1997) Neural Comput , vol.9 , Issue.1 , pp. 185-204
    • Setiono, R.1
  • 31
    • 53749105298 scopus 로고    scopus 로고
    • Enhancing the generalization ability of neural networks through controlling the hidden layers
    • W. Wan, S. Mabu, K. Shimada, K. Hirasawa, Enhancing the generalization ability of neural networks through controlling the hidden layers, J. Hu, App. Soft Comput. 9, 404-414, 2009
    • (2009) J. Hu, App. Soft Comput , vol.9 , pp. 404-414
    • Wan, W.1    Mabu, S.2    Shimada, K.3    Hirasawa, K.4
  • 32
    • 0028413960 scopus 로고
    • A simple and effective method for removal of hidden units and weights
    • M. Hagiwara, A simple and effective method for removal of hidden units and weights, Neurocomputing, 6, 207-218, 1994
    • (1994) Neurocomputing , vol.6 , pp. 207-218
    • Hagiwara, M.1
  • 34
    • 65149084176 scopus 로고    scopus 로고
    • Two phase construction of multilayer perceptrons using Information Theory
    • H.-J. Xing, B.-G. Hu, Two phase construction of multilayer perceptrons using Information Theory, IEEE T. Neural Networ. 20 (4), 715-721, 2009
    • (2009) IEEE T. Neural Networ , vol.20 , Issue.4 , pp. 715-721
    • Xing, H.-J.1    Hu, B.-G.2
  • 35
    • 78649288454 scopus 로고    scopus 로고
    • A node pruning algorithm for feedforward neural network based on neural complexity
    • Dalian, 13-15 August
    • Z. Zhang, J. Qiao, A Node Pruning Algorithm for Feedforward Neural Network Based on Neural Complexity, In: Int. Conf. on Intelligent Control and Information Processing, Dalian, 13-15 August 2010, 406-410
    • (2010) Int. Conf. on Intelligent Control and Information Processing , pp. 406-410
    • Zhang, Z.1    Qiao, J.2
  • 36
    • 0001420440 scopus 로고
    • The evolution of connectivity: Pruning neural networks using genetic algorithms
    • IEE Press, Washington DC
    • D. Whitley, C. Bogart, The evolution of connectivity: Pruning neural networks using genetic algorithms, In: Int. Joint Conf. Neural Networks, 1 (IEE Press, Washington DC, 1990) 134-137
    • (1990) Int. Joint Conf. Neural Networks , vol.1 , pp. 134-137
    • Whitley, D.1    Bogart, C.2
  • 37
    • 33847675397 scopus 로고    scopus 로고
    • Optimizing feedforward artificial neural network architecture
    • P. G. Benardos, G.-C. Vosniakos, Optimizing feedforward artificial neural network architecture, Eng. App. Artif. Intelligence, 20, 365-382, 2007
    • (2007) Eng. App. Artif. Intelligence , vol.20 , pp. 365-382
    • Benardos, P.G.1    Vosniakos, G.-C.2
  • 38
    • 32544452874 scopus 로고    scopus 로고
    • Hidden neuron pruning of multilayer perceptrons using a quantified sensitivity measure
    • X. Zeng, D. S.Yeung, Hidden neuron pruning of multilayer perceptrons using a quantified sensitivity measure, Neuro Comput. 69, 825-837, 2006
    • (2006) Neuro Comput , vol.69 , pp. 825-837
    • Zeng, X.1    Yeung, D.S.2
  • 39
    • 33644884686 scopus 로고    scopus 로고
    • A node pruning algorithm based on a fourier amplitude sensitivity test method
    • P. Lauret, E. Fock, T. A. Mara, A Node Pruning Algorithm Based on a Fourier Amplitude Sensitivity Test Method, IEEE T. Neural Networ. 17 (2), 273-293, 2006
    • (2006) IEEE T. Neural Networ , vol.17 , Issue.2 , pp. 273-293
    • Lauret, P.1    Fock, E.2    Mara, T.A.3
  • 43
    • 0032674833 scopus 로고    scopus 로고
    • A formal selection and pruning algorithm for feedforward artificial neural network optimization
    • P. V. S. Ponnapallii, K. C. Ho, M. Thomson, A formal selection and pruning algorithm for feedforward artificial neural network optimization, IEEE T. Neural Networ., 10 (4), 964-968, 1999
    • (1999) IEEE T. Neural Networ. , vol.10 , Issue.4 , pp. 964-968
    • Ponnapallii, P.V.S.1    Ho, K.C.2    Thomson, M.3
  • 44
    • 0029256585 scopus 로고
    • Determining input features for multilayer perceptrons
    • L. M. Belue, K. W. Bauer, Determining input features for multilayer perceptrons, Neurocomputing 7, 111-121, 1995
    • (1995) Neurocomputing , vol.7 , pp. 111-121
    • Belue, L.M.1    Bauer, K.W.2
  • 45
    • 84855534224 scopus 로고    scopus 로고
    • A novel pruning algorithm for optimizing feedforward neural network of classification problems
    • G. Augasta, T. Kathirvalavakumar, A Novel Pruning Algorithm for Optimizing Feedforward Neural Network of Classification Problems, Neural Process. Lett. 34 (3), 241-258, 2011
    • (2011) Neural Process. Lett , vol.34 , Issue.3 , pp. 241-258
    • Augasta, G.1    Kathirvalavakumar, T.2
  • 46
    • 27644501247 scopus 로고    scopus 로고
    • A comparative study of neural network optimization techniques
    • Norwich, UK, 2-4 April, 1997, Artificial Nets and Genetic Algorithms Springer
    • T. Ragg, H. Braun, H. Landsberg, A comparative study of neural network optimization Techniques, In 13th International Conf. on Machine Learning, Norwich, UK, 2-4 April, 1997, Artificial Nets and Genetic Algorithms (Springer, 1997) 341-345
    • (1997) 13th International Conf. on Machine Learning , pp. 341-345
    • Ragg, T.1    Braun, H.2    Landsberg, H.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.