Hinton等人提出的深度机器学习,掀起了神经网络研究的又一个浪潮.介绍了深度机器学习的基本概念和基本思想.对于目前比较成熟的深度机器学习结构深度置信网DBNs和约束Boltzmann机(RBM)的结构和无监督贪婪学习算法作了比较详细的介绍和比较,并对算法的改进方向提出了有建设性的意见,对深度机器学习的未来发展方向和目前存在的问题进行了深刻的分析.
[1] HAYKIN S. Neural Networks:A comprehensive foundation [M]. New York:Prentice-hall 1999.
[2] Yoshua Bengio. Learning Deep Architectures for AI [J]. Foundations and trends in machine learning 2009, 1(1).
[3] HINTON G E, MCCLELLAND J L, RUMELHART D E. Distributed Representations [M]. Cambridge, MA:The MIT Press 1986.
[4] Geoffrey E. Hinton, Simon Osindero, Yee-Whye Teh. A Fast Learning Algorithm for Deep Belief Nets [J]. Neural computation 2006, 7(7).
[5] HUBEL D, WIESEL T. Receptive fields, binocular interaction, and functional architecture in the cat's visual cortex [J]. The Journal of Physiology 1962, 160.
[6] LECUNY, KAVUKCUOGLUK, FARABET C. Convolutional networks and applications in vision [A]. France:Paris 2010.
[7] LASERSON J. From neural networks to deep learning:zeroing in on the human brain [J]. XRDS 2011, 18(01).
[8] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE 1998, 11(11).
[9] ERHAND, BENGIO Y, COURVILE A. Why does unsupervised pre-training help deep learning [J]. Journal of Machine Learning Research 2010, 11.
[10] BENGIO Y, LAMBLIN P, POPOVICI D. Greedy layer-wise training of deep networks [J]. Advances in Neural Information Processing Systems 2007, 19.
[11] BISHOP C M. Pattern recognition and machine learning [M]. New York:springer-verlag 2006.
[12] Hinton GE, Dayan P, Frey BJ, Neal RM. THE WAKE-SLEEP ALGORITHM FOR UNSUPERVISED NEURAL NETWORKS [J]. Science 1995, 5214(5214).
