Supervised autoencoders: Improving generalization performance with unsupervised regularizers
作者： Lei Le , Martha White , Andrew Patterson
DOI:
关键词:
摘要: … In this work, we investigate an auxiliary-task model for which we can make generalization guarantees, called a supervised auto-encoder (SAE). A SAE is a neural network that predicts …
nips.cc参考文章(26)
Yaser S Abu-Mostafa, Learning from hints in neural networks Journal of Complexity. ,vol. 6, pp. 192- 198 ,(1990) , 10.1016/0885-064X(90)90006-Y
Shai Ben-David, Reba Schuller, Exploiting Task Relatedness for Multiple Task Learning conference on learning theory. pp. 567- 580 ,(2003) , 10.1007/978-3-540-45167-9_41
Jonathan Baxter, Learning internal representations conference on learning theory. pp. 311- 320 ,(1995) , 10.1145/225298.225336
Pierre Baldi, Kurt Hornik, Neural networks and principal component analysis: learning from examples without local minima Neural Networks. ,vol. 2, pp. 53- 58 ,(1989) , 10.1016/0893-6080(89)90014-2
Yoshua Bengio, Hugo Larochelle, Pascal Lamblin, Dan Popovici, Greedy Layer-Wise Training of Deep Networks neural information processing systems. ,vol. 19, pp. 153- 160 ,(2006)
Tong Zhang, Covering number bounds of certain regularized linear function classes Journal of Machine Learning Research. ,vol. 2, pp. 527- 550 ,(2002) , 10.1162/153244302760200713
Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition Proceedings of the IEEE. ,vol. 86, pp. 2278- 2324 ,(1998) , 10.1109/5.726791
H. Bourlard, N. Morgan, Generalization and Parameter Estimation in Feedforward Nets: Some Experiments neural information processing systems. ,vol. 2, pp. 630- 637 ,(1989)
Rich Caruana, Virginia R. de Sa, Promoting Poor Features to Supervisors: Some Inputs Work Better as Outputs neural information processing systems. ,vol. 9, pp. 389- 395 ,(1996)
Stefan Wager, Sida Wang, Percy S Liang, Dropout Training as Adaptive Regularization neural information processing systems. ,vol. 26, pp. 351- 359 ,(2013)