A fast pruning algorithm for neural network

Tien Tzu Hsueh Pao/Acta Electronica Sinica

Volumn 38, Issue 4, 2010, Pages 830-834

  Qiao, Jun Fei ^a   Li, Miao ^a   Liu, Jiang ^a  

^a BEIJING UNIVERSITY OF TECHNOLOGY   (China)

Author keywords

Fourier amplitude; Neural network pruning; Sensitivity

Indexed keywords

COMPACT STRUCTURES; FOURIER AMPLITUDE; FOURIER AMPLITUDE SENSITIVITY TESTS; FOURIER AMPLITUDES; FUNDAMENTAL FREQUENCIES; HIDDEN LAYERS; HIDDEN NEURONS; INPUT FACTORS; NONLINEAR FUNCTIONS; OUTPUT VALUES; PRUNING ALGORITHMS; QUALITY PARAMETERS; REDUNDANT HIDDEN NEURONS; SENSITIVITY VALUES; SOFT MEASUREMENT;

CHEMICAL OXYGEN DEMAND; FOURIER TRANSFORMS; NEURONS; OXYGEN; SEWAGE; WASTEWATER;

NEURAL NETWORKS;

EID: 77953167019     PISSN: 03722112     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (9)

1. Y Le Cun, J S Denker, S A Solla. Optimal brain damage[A]. Advances in Neural Information Processing Systems[C]. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc, 1990, 2: 598-605.
2. B Hassibi, D G Stork. Second-order derivatives for network pruning: optimal brain surgeon[A]. Advances in Neural Information Processing Systems[C]. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc, 1993, 5: 164-171.
3. T Cibas, F F Soulie, P Gallinari, S Raudys. Variable selection with neural networks[J]. Neurocomputing, 1996, 12(2-3): 223-248.
4. M E Ricotti, E Zio. Neural network approach to sensitivity and uncertainty analysis[J]. Reliability Engineering and System Safety, 1999, 64(1): 59-71.
5. Saltelli S Tarantola, K-S Chan. A quantitative model independent method for global sensitivity analysis of model output[J]. Technometrics, 1999, 41(1): 39-56.
6. Philippe Lauret, Eric Fock, Thierry Alex Mara. A node pruning algorithm based on a Fourier amplitude sensitivity test method[J]. IEEE Transactions on Neural Networks, 2006, 17(2): 273-293.
7. R I Cukier, C M Fortuin, K E Shuler, A G Petscheck, J H Schaibly. Study of the sensitivity of coupled reaction systems to uncertainties in rate coefficients[J]. Journal of Chemical Physics, 1973, 59(8): 3873-3878.
8. Christian Schittenkopf, Gustavo Deco, Wilfried Brauer. Two strategies to avoid over fitting in feed forward networks[J]. Neural networks, 1997, 10(3): 505-516.
9. P Engelbretch. A new pruning heuristic based on variance analysis of sensitivity information[J]. IEEE Transactions on Neural Network, 2001, 12(6): 1386-1399.