Hinton, G. E., Osindero, S. and Teh, Y.,A fast learning algorithm for deep belief nets. Neural Computation 18: 1527-1554, 2006
Yoshua Bengio, Pascal Lamblin, Dan Popovici and Hugo Larochelle,Greedy LayerWise Training of Deep Networks, in J. Platt et al. (Eds), Advances in Neural Information Processing Systems 19 (NIPS 2006), pp. 153-160, MIT Press, 2007
Marc’Aurelio Ranzato, Christopher Poultney, Sumit Chopra and Yann LeCun Efficient Learning of Sparse Representations with an Energy-Based Model, in J. Platt et al. (Eds), Advances in Neural Information Processing Systems (NIPS 2006), MIT Press, 2007
在这三篇论文中以下主要原理被发现:
表示的无监督学习被用于(预)训练每一层;
在一个时间里的一个层次的无监督训练,接着之前训练的层次。在每一层学习到的表示作为下一层的输入;
用有监督训练来调整所有层(加上一个或者更多地用于产生预测的附加层);
DBNs在每一层中利用用于表示的无监督学习RBMs。Bengio et al paper 探讨和对比了RBMs和auto-encoders(通过一个表示的瓶颈内在层预测输入的神经网路)。Ranzato et al paper在一个convolutional架构的上下文中使用稀疏auto-encoders(类似于稀疏编码)。Auto-encoders和convolutional架构将在以后的课程中讲解。
从2006年以来,大量的关于深度学习的论文被发表。
套用
1.计算机视觉
ImageNet Classification with Deep Convolutional Neural Networks, Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton, NIPS 2012.
Learning Hierarchical Features for Scene Labeling, Clement Farabet, Camille Couprie, Laurent Najman and Yann LeCun, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013.
Learning Convolutional Feature Hierarchies for Visual Recognition, Koray Kavukcuoglu, Pierre Sermanet, Y-Lan Boureau, Karol Gregor, Michaël Mathieu and Yann LeCun, Advances in Neural Information Processing Systems (NIPS 2010), 23, 2010.
很多机构在开展研究,2013年,Tomas Mikolov,Kai Chen,Greg Corrado,Jeffrey Dean发表论文Efficient Estimation of Word Representations in Vector Space建立word2vector模型,与传统的词袋模型(bag of words)相比,word2vector能够更好地表达语法信息。深度学习在自然语言处理等领域主要套用于机器翻译以及语义挖掘等方面。