2LEE S W. Off-line recognition of totolly unconstrained handwritten numerals using multilayer cluster neural network[J].IEEE trans pattern anal math intell,1996,18(6):648-652.
4Lam.L, W.Lee.S, Suen C.Y. Thinning Methodologies-A Comprehensive Survey[D]. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1992,14(9):879.
5Mukhlisin M,El-Shafie A , Taha M R. Regularized versus non-regularizedneural network model for prediction of saturated soil-watercontent on weathered granite soil formation [J]. Neural Computing& Applications,2 0 1 2,21(3) :543 -553.
6Srivastava N, Hinton G, Krizhevsky A , et al. Dropout: A SimpleWay to Prevent Neural Networks from Overfitting [J]. Journal ofMachine Learning Research,2 0 1 4,15(1) :1929 -1958.
7Krizhevsky A , Sutskever I , Hinton G E , et al. ImageNet Classificationwith Deep Convolutional Neural Networks [C]. Advances inNeural Information Processing Systems,2012.
8Baldi P , Sadowski P. The Dropout Learning Algorithm[J]. ArtificialIntelligence,2 0 1 4,210(3) :78 -122.
9Wan L, Zeiler M, Zhang S, et al. Regularization of Neural Networksusing Drop Connect [C]. Proceedings of International Conferenceon Machine Learning,2013.
10Alexandras Iosifidis, Anastasios Tefas, Ioannis Pitas. DropELM:Fast neural network regularization with Dropout and DropConnect[J]. Neurocomputing,2015(162) :57 - 6 6.
