Can threshold networks be trained directly
作者： Guang-Bin Huang , Qin-Yu Zhu , K.Z. Mao , Chee-Kheong Siew , P. Saratchandran
DOI: 10.1109/TCSII.2005.857540
关键词:
摘要: … small, the gain parameter is gradually increased during the training until the slope of the sigmoid is sufficiently large to allow a transfer to a threshold network with the same architecture. …
sci-hub.se 参考文章(13)
V.P. Plagianakos, G.D. Magoulas, N.K. Nousis, M.N. Vrahatis, Training multilayer networks with discrete activation functions international joint conference on neural network. ,vol. 4, pp. 2805- 2810 ,(2001) , 10.1109/IJCNN.2001.938819
E.M. Corwin, A.M. Logar, W.J.B. Oldham, An iterative method for training multilayer networks with threshold functions IEEE Transactions on Neural Networks. ,vol. 5, pp. 507- 508 ,(1994) , 10.1109/72.286926
Eric B Baum, On the capabilities of multilayer perceptrons Journal of Complexity. ,vol. 4, pp. 193- 215 ,(1988) , 10.1016/0885-064X(88)90020-9
D.J. Toms, Training binary node feedforward neural networks by back propagation of error Electronics Letters. ,vol. 26, pp. 1745- 1746 ,(1990) , 10.1049/EL:19901121
P.L. Bartlett, The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network IEEE Transactions on Information Theory. ,vol. 44, pp. 525- 536 ,(1998) , 10.1109/18.661502
S. Tamura, M. Tateishi, Capabilities of a four-layered feedforward neural network: four layers versus three IEEE Transactions on Neural Networks. ,vol. 8, pp. 251- 255 ,(1997) , 10.1109/72.557662
S.E. Hampson, D.J. Volper, Representing and learning Boolean functions of multivalued features systems man and cybernetics. ,vol. 20, pp. 67- 80 ,(1990) , 10.1109/21.47810
P.L. Barlett, T. Downs, Using random weights to train multilayer networks of hard-limiting units IEEE Transactions on Neural Networks. ,vol. 3, pp. 202- 210 ,(1992) , 10.1109/72.125861
R.M. Goodman, Zheng Zeng, A learning algorithm for multi-layer perceptrons with hard-limiting threshold units ieee workshop on neural networks for signal processing. ,vol. 1, pp. 219- 228 ,(1994) , 10.1109/NNSP.1994.366045
Guang-Bin Huang, Qin-Yu Zhu, Chee-Kheong Siew, Extreme learning machine: a new learning scheme of feedforward neural networks international joint conference on neural network. ,vol. 2, pp. 985- 990 ,(2004) , 10.1109/IJCNN.2004.1380068