Whiteout: Gaussian Adaptive Noise Regularization in Deep Neural Networks

A. Ivakhnenko, “Polynomial theory of complex systems,” IEEE Transactions on Systems, Man and Cybernetics , vol. 4, pp. 364–378, 1971

1971

Earlier work this paper cites.

D. C. Plaut, S. J. Nowlan, and G. E. Hinton, “Experiments on learning by back-propagation,” Tech. Rep. CMU-CS-86-126 , 1986

1986

Earlier work this paper cites.

J. Sietsma and R. J. F. Dow, “Neural network pruning - why and how,” Proceedings of the IEEE International Conferences on Neural Networks , vol. 1, pp. 325–333, 1988

1988

Earlier work this paper cites.

M. C. Mozer and P. Smolensky, “Skeletonization: A technique for trimming the fat from a network via relevance assessment,” 1989, pp. 107–115

1989

Earlier work this paper cites.

S. J. Hanson and L. Y. Pratt, “Comparing biases for minimal network construction with back-propagation,” 1989, pp. 177–185

1989

Earlier work this paper cites.

Y. L. Cun, J. S. Denker, and S. A. Solla, “Optimal brain damage,” 1990, pp. 598–605

1990

Earlier work this paper cites.

K. Hornik, “Approximation capabilities of multilayer feedforward networkss,” Neural Networks, , vol. 4, no. 2, pp. 251–257, 1991

1991

Earlier work this paper cites.

L. Holmstrom and P. Koistinen, “Using additive noise in back-propagation training,” IEEE transactions on neural networks , vol. 3, no. 1, pp. 24–38, 1992

1992

Earlier work this paper cites.

K. Matsuoka, “Noise injection into inputs in back-propagation learning,” IEEE Tranactions on Systems, Man, and Cybernetics , vol. 22, no. 3, pp. 436–440, 1992

1992

Earlier work this paper cites.

I. Frank and J. Friedman, “A statistical view of some chemometrics regression tools,” Technometrics , vol. 35, no. 2, pp. 109–135, 1993

1993

Earlier work this paper cites.

C. M. Bishop, “Training with noise is equivalent to Tikhonov regularization,” Neural Computation , vol. 7, no. 1, pp. 108–116, 1995

1995

Earlier work this paper cites.

G. Lugosi, “Nonparametric estimation via empirical risk minimization,” IEEE Transactions on Information Theory , vol. 41, 1995

1995

Earlier work this paper cites.

G. An, “The Effects of Adding Noise During Backpropagation Training on a Generalization Performance,” Neural Computation , vol. 8, pp. 643–674, 1996

1996

Earlier work this paper cites.

Y. Grandvalet, S. Canu, and S. Boucheron, “Noise Injection: Theoretical Prospects,” Neural Computation , vol. 9, no. 5, pp. 1093–1108, 1997

1997

Cited alongside, same era.

N. Srebro and A. Shraibman, “Rank, trace-norm and max-norm,” Proceedings of the 18th annual conference on Learning Theory, COLT’05 , pp. 545–560, 2005

2005

Cited alongside, same era.

T. Zhang and B. Yu, “Boosting with early stopping: Convergence and consistency,” The Annals of Statistics , vol. 33, no. 4, pp. 1538–1579, 2005

2005

Cited alongside, same era.

H. Zou and T. Hastie, “Regularization and variable selection via the elastic net,” Journal of the Royal Statistical Society: Series B , vol. 67, no. 2, pp. 301–320, 2005

2005

Cited alongside, same era.

G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science , vol. 313, pp. 504–507, 2006

G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov., “Improving neural networks by preventing co-adaptation of feature detectors,” arXiv:1207.0580 , 2012

Original

2012

Later among the works it cites.

L. Wan, M. Zeiler, S. Zhang, Y. LeCun, and R. Fergus, “Regularization of neural networks using dropConnect,” Proceedings of Machine Learning Research , vol. 28, no. 3, pp. 1058–1066, 2013

2013

Later among the works it cites.

I. J. Goodfellow, D. Warde-Farley, M. Mirza, A. Courville, and Y. Bengio, “Maxout Networks,” Proceedings of the 30th International Conference on Machine Learning (ICML) , vol. 28, pp. 1319–1327, 2013

2013

Later among the works it cites.

S. Wang and C. D. Manning, “Fast dropout training,” Proceedings of the 30th International Conference on Machine Learning , vol. 28, pp. 118–126, 2013

2013

Later among the works it cites.