Where do features come from?WOSEI
摘要
It is possible to learn multiple layers of non-linear features by backpropagating error derivatives through a feedforward neural network. This is a very effective learning procedure when there is a huge amount of labeled training data, but for many learning tasks very few labeled examples are available. In an effort to overcome the need for labeled data, several different generative models were developed that learned interesting features by modeling the higher order statistical structure of a set of input vectors. One of these generat...更多
- 1Yanxia Zhang, Lu Yang, Binghao Meng, Hong Cheng, Yong Zhang, Qian Wang, Jiadan Zhu. On the Quantitative Analysis of Sparse RBMs.PCM, pp. 449-458, 2016.
- 2Decebal Constantin Mocanu, Elena Mocanu, Phuong H. Nguyen, Madeleine Gibescu, Antonio Liotta. A topological insight into restricted Boltzmann machines.Machine Learning, 2016.
- 3Jia Liu, Maoguo Gong, Jiaojiao Zhao, Hao Li, Licheng Jiao. Difference representation learning using stacked restricted Boltzmann machines for change detection in SAR images.Soft Comput., pp. 4645-4657, 2016.
- 4Eastwood, M.; Jayne, C.. Dual Deep Neural Network approach to matching data in different modes.Neural Networks, pp. 1688-1694, 2014.
- 5Pikrakis, A.; Theodoridis, S.. Speech-music discrimination: A deep learning perspective.Signal Processing Conference, pp. 616-620, 2014.
- 6Xiao Sun, Chengcheng Li, Wanyi Xu, Fuji Ren. Chinese Microblog Sentiment Classification Based on Deep Belief Nets with Extended Multi-Modality Features.ICDM Workshops, pp. 928-935, 2014.
- 7Marc-Alexandre Côté, Hugo Larochelle. An Infinite Restricted Boltzmann Machine.Neural Computation, 2015.
- 8Stefan Elfwing, Eiji Uchibe, Kenji Doya. Expected energy-based restricted Boltzmann machine for classification.Neural Networks, pp. 29-38, 2015.
- 9Chen, C.; Zhang, C.; Chen, L.; Gan, M.. Fuzzy Restricted Boltzmann Machine and Its Fast Learning Algorithm.Fuzzy Systems, IEEE Transactions , pp. 12015.
- 10Fangxiang Feng, Ruifan Li, Xiaojie Wang. Deep correspondence restricted Boltzmann machine for cross-modal retrieval.Neurocomputing, pp. 50-60, 2015.
- 11Adriano Barra, Alberto Bernacchia, Enrica Santucci, Pierluigi Contucci. On the equivalence of Hopfield networks and Boltzmann Machines.Neural Networks, pp. 1-9, 2012.
- 12Hieu Trung Huynh, Yonggwan Won. Small Number of Hidden Units for ELM with Two-Stage Linear Model.IEICE Transactions, pp. 1042-1049, 2008.
- 13Hugo Larochelle, Yoshua Bengio, Jérôme Louradour, Pascal Lamblin. Exploring Strategies for Training Deep Neural Networks.Journal of Machine Learning Research, pp. 1-40, 2009.
- 14Chun-Xia Zhang, Jiang-She Zhang, Nan-Nan Ji, Gao Guo. Learning ensemble classifiers via restricted Boltzmann machines.Pattern Recognition Letters, pp. 161-170, 2014.
- 15Geoffrey E. Hinton, Learning multiple layers of representation.Trends in Cognitive Sciences, pp. 428-434, 2007.
- 16Nicolas Le Roux, Yoshua Bengio. Representational power of restricted boltzmann machines and deep belief networks.Neural Computation, pp. 1631-1649, 2008.
- 17Mostafa A. Salama, Aboul Ella Hassanien, Aly A. Fahmy. Deep Belief Network for clustering and classification of a continuous data.ISSPIT, pp. 473-477, 2010.
- 19Hannes Schulz, Andreas Müller, Sven Behnke. Exploiting local structure in Boltzmann machines.Neurocomputing, pp. 1411-1417, 2011.
- 20Hugo Larochelle, Yoshua Bengio. Classification using discriminative restricted Boltzmann machines.ICML, pp. 536-543, 2008.
个人信息
Cognitive Science Society Annual Conference, pp. 1078-1101, 2014.
被引用次数:39|引用|19
标签
作者
评论