A modified version of a formal pruning algorithm based on local relative variance analysis
作者： N. Fnaiech , S. Abid , N. Fnaiech , S. Abid , F. Fnaiech
DOI: 10.1109/ISCCSP.2004.1296579
关键词:
摘要: A modified version of a formal pruning algorithm initially proposed by Englebercht [November, 2001] using variance analysis sensitivity is presented. We propose new modification the applying procedure on each layer starting from output to input layer. Contrarily, work where performed entire net that we denote in this paper global pruning, shall prune with use decision based local parameter nullity coefficient (LPVN). These coefficients are then classified an ordered list which allows making examples showing some cases can reach about 30% improvement terms and neurons removal order get best neural network pruned. comparison study given real world learning generalization.
etsmtl.ca
sci-hub.se 参考文章(12)
M. Hagiwara, Removal of hidden units and weights for back propagation networks international joint conference on neural network. ,vol. 1, pp. 351- 354 ,(1993) , 10.1109/IJCNN.1993.713929
N. Fnaiech, F. Fnaiech, M. Cheriet, A new feedforward neural network pruning algorithm: SSM-iterative pruning (SSMIP) systems, man and cybernetics. ,vol. 4, pp. 6- ,(2002) , 10.1109/ICSMC.2002.1173310
M. Najim, S. Abid, F. Fnaiech, A new Neural Network pruning method based on the singular value decomposition and the weight initialisation european signal processing conference. pp. 1- 4 ,(2002) , 10.5281/ZENODO.38073
F. Fnaiech, N. Fnaiech, M. Najim, A new feedforward neural network hidden layer neuron pruning algorithm international conference on acoustics, speech, and signal processing. ,vol. 2, pp. 1277- 1280 ,(2001) , 10.1109/ICASSP.2001.941158
A.P. Engelbrecht, A new pruning heuristic based on variance analysis of sensitivity information IEEE Transactions on Neural Networks. ,vol. 12, pp. 1386- 1399 ,(2001) , 10.1109/72.963775
M. Cottrell, B. Girard, Y. Girard, M. Mangeas, C. Muller, Neural modeling for time series: A statistical stepwise method for weight elimination IEEE Transactions on Neural Networks. ,vol. 6, pp. 1355- 1364 ,(1995) , 10.1109/72.471372
Yann LeCun, John Denker, Sara Solla, None, Optimal Brain Damage neural information processing systems. ,vol. 2, pp. 598- 605 ,(1989)
G. Castellano, A.M. Fanelli, M. Pelillo, An iterative pruning algorithm for feedforward neural networks IEEE Transactions on Neural Networks. ,vol. 8, pp. 519- 531 ,(1997) , 10.1109/72.572092
P.V.S. Ponnapalli, K.C. Ho, M. Thomson, A formal selection and pruning algorithm for feedforward artificial neural network optimization IEEE Transactions on Neural Networks. ,vol. 10, pp. 964- 968 ,(1999) , 10.1109/72.774273
B. Hassibi, D.G. Stork, G.J. Wolff, Optimal Brain Surgeon and general network pruning IEEE International Conference on Neural Networks. pp. 293- 299 ,(1993) , 10.1109/ICNN.1993.298572