bibli.bib

@article{mnistlecun,
    author = {Lecun, Yann and Cortes, Corinna},
    citeulike-article-id = {599493},
    citeulike-linkout-0 = {http://yann.lecun.com/exdb/mnist/},
    keywords = {ai, mnist, recognition},
    posted-at = {2009-03-20 17:02:13},
    priority = {2},
    title = {{The MNIST database of handwritten digits}},
    url = {http://yann.lecun.com/exdb/mnist/}
}
@article{DBLP:journals/corr/abs-1206-5538,
  author    = {Yoshua Bengio and
               Aaron C. Courville and
               Pascal Vincent},
  title     = {Unsupervised Feature Learning and Deep Learning: A Review
               and New Perspectives},
  journal   = {CoRR},
  volume    = {abs/1206.5538},
  year      = {2012},
  ee        = {http://arxiv.org/abs/1206.5538},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}

@article{Hinton:2006:FLA:1161603.1161605,
 author = {Hinton, Geoffrey E. and Osindero, Simon and Teh, Yee-Whye},
 title = {A Fast Learning Algorithm for Deep Belief Nets},
 journal = {Neural Comput.},
 issue_date = {July 2006},
 volume = {18},
 number = {7},
 month = jul,
 year = {2006},
 issn = {0899-7667},
 pages = {1527--1554},
 numpages = {28},
 url = {http://dx.doi.org/10.1162/neco.2006.18.7.1527},
 doi = {10.1162/neco.2006.18.7.1527},
 acmid = {1161605},
 publisher = {MIT Press},
 address = {Cambridge, MA, USA},
} }

@incollection{Bengio2007,
  added-at = {2010-02-27T01:05:18.000+0100},
  address = {Cambridge, MA},
  author = {Bengio, Y. and Lamblin, P. and Popovici, D. and Larochelle, H.},
  biburl = {http://www.bibsonomy.org/bibtex/2629899884d8653b834814d9f8c4fa395/tb2332},
  booktitle = {Advances in Neural Information Processing Systems 19},
  editor = {Sch\"{o}lkopf, B. and Platt, J. and Hoffman, T.},
  interhash = {85cb1f82cef93c41ce1ba302b965c798},
  intrahash = {629899884d8653b834814d9f8c4fa395},
  keywords = {imported},
  owner = {thierry},
  pages = {153--160},
  publisher = {MIT Press},
  timestamp = {2010-02-27T01:05:18.000+0100},
  title = {Greedy layer-wise training of deep networks},
  year = 2007
}

@article{HintonSalakhutdinov2006b,
  abstract = {High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuning the weights in such "autoencoder" networks, but this works well only if the initial weights are close to a good solution. We describe an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.},
  added-at = {2008-07-15T10:05:18.000+0200},
  author = {Hinton, G E and Salakhutdinov, R R},
  biburl = {http://www.bibsonomy.org/bibtex/2135bbce97b449ddf5fca7be88102b53c/tmalsburg},
  description = {Reducing the dimensionality of data with neural ne...[Science. 2006] - PubMed Result},
  doi = {10.1126/science.1127647},
  interhash = {019918b82518b74f443a22dc58a0117f},
  intrahash = {135bbce97b449ddf5fca7be88102b53c},
  journal = {Science},
  keywords = {dimensionalityreduction neuralnetworks parameterestimation},
  month = Jul,
  number = 5786,
  pages = {504-507},
  pmid = {16873662},
  timestamp = {2008-07-15T10:05:18.000+0200},
  title = {Reducing the dimensionality of data with neural networks},
  volume = 313,
  year = 2006
}
@inproceedings{DBLP:conf/icml/NairH10,
  author    = {Vinod Nair and
               Geoffrey E. Hinton},
  title     = {Rectified Linear Units Improve Restricted Boltzmann Machines},
  booktitle = {ICML},
  year      = {2010},
  pages     = {807-814},
  ee        = {http://www.icml2010.org/papers/432.pdf},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}
@proceedings{DBLP:conf/icml/2010,
  editor    = {Johannes Furnkranz and
               Thorsten Joachims},
  title     = {Proceedings of the 27th International Conference on Machine
               Learning (ICML-10), June 21-24, 2010, Haifa, Israel},
  booktitle = {ICML},
  publisher = {Omnipress},
  year      = {2010},
  isbn      = {978-1-60558-907-7},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}

@article{DBLP:journals/corr/abs-1207-0580,
  author    = {Geoffrey E. Hinton and
               Nitish Srivastava and
               Alex Krizhevsky and
               Ilya Sutskever and
               Ruslan Salakhutdinov},
  title     = {Improving neural networks by preventing co-adaptation of
               feature detectors},
  journal   = {CoRR},
  volume    = {abs/1207.0580},
  year      = {2012},
  ee        = {http://arxiv.org/abs/1207.0580},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}
@article{DBLP:journals/corr/abs-1206-5533,
  author    = {Yoshua Bengio},
  title     = {Practical recommendations for gradient-based training of
               deep architectures},
  journal   = {CoRR},
  volume    = {abs/1206.5533},
  year      = {2012},
  ee        = {http://arxiv.org/abs/1206.5533},
}
@inproceedings{conf/icml/WanZZLF13,
  added-at = {2013-12-08T17:48:24.000+0100},
  author = {Wan, Li and Zeiler, Matthew D. and Zhang, Sixin and LeCun, Yann and Fergus, Rob},
  biburl = {http://www.bibsonomy.org/bibtex/25e2a0d899d79d425fe876ec39cb08765/prlz77},
  booktitle = {ICML (3)},
  ee = {http://jmlr.org/proceedings/papers/v28/wan13.html},
  interhash = {818d79b17f088fd88c0200625c7a43ea},
  intrahash = {5e2a0d899d79d425fe876ec39cb08765},
  keywords = {DropConnect Networks Neural Regularization of using},
  pages = {1058-1066},
  publisher = {JMLR.org},
  series = {JMLR Proceedings},
  timestamp = {2013-12-08T17:48:24.000+0100},
  title = {Regularization of Neural Networks using DropConnect.},
  url = {http://dblp.uni-trier.de/db/conf/icml/icml2013.htmlWanZZLF13},
  volume = 28,
  year = 2013
}
@article{DBLP:journals/corr/abs-1202-2745,
  author    = {Dan C. Ciresan and
               Ueli Meier and
               J{\"u}rgen Schmidhuber},
  title     = {Multi-column Deep Neural Networks for Image Classification},
  journal   = {CoRR},
  volume    = {abs/1202.2745},
  year      = {2012},
  ee        = {http://arxiv.org/abs/1202.2745},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}
@ARTICLE{2013arXiv1302.4389G,
   author = {{Goodfellow}, I.~J. and {Warde-Farley}, D. and {Mirza}, M. and 
	{Courville}, A. and {Bengio}, Y.},
    title = "{Maxout Networks}",
  journal = {ArXiv e-prints},
archivePrefix = "arXiv",
   eprint = {1302.4389},
 primaryClass = "stat.ML",
 keywords = {Statistics - Machine Learning, Computer Science - Learning},
     year = 2013,
    month = feb,
   adsurl = {http://adsabs.harvard.edu/abs/2013arXiv1302.4389G},
  adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}
@article{journals/corr/abs-1203-1513,
  added-at = {2012-10-10T00:00:00.000+0200},
  author = {Bruna, Joan and Mallat, Stéphane},
  biburl = {http://www.bibsonomy.org/bibtex/24a4605c67f7cee3a3eb8086e0e313745/dblp},
  ee = {http://arxiv.org/abs/1203.1513},
  interhash = {6fdc274fb99f514ca1c527b849a30b06},
  intrahash = {4a4605c67f7cee3a3eb8086e0e313745},
  journal = {CoRR},
  keywords = {dblp},
  timestamp = {2012-10-10T00:00:00.000+0200},
  title = {Invariant Scattering Convolution Networks},
  url = {http://dblp.uni-trier.de/db/journals/corr/corr1203.htmlabs-1203-1513},
  volume = {abs/1203.1513},
  year = 2012
}
@book{Hassoun:1995:FAN:526717,
 author = {Hassoun, Mohamad H.},
 title = {Fundamentals of Artificial Neural Networks},
 year = {1995},
 isbn = {026208239X},
 edition = {1st},
 publisher = {MIT Press},
 address = {Cambridge, MA, USA}
} 

@article{Baldi:1989:NNP:70359.70362,
 author = {Baldi, P. and Hornik, K.},
 title = {Neural Networks and Principal Component Analysis: Learning from Examples Without Local Minima},
 journal = {Neural Netw.},
 issue_date = {1989},
 volume = {2},
 number = {1},
 month = jan,
 year = {1989},
 issn = {0893-6080},
 pages = {53--58},
 numpages = {6},
 url = {http://dx.doi.org/10.1016/0893-6080(89)90014-2},
 doi = {10.1016/0893-6080(89)90014-2},
 acmid = {70362},
 publisher = {Elsevier Science Ltd.},
 address = {Oxford, UK, UK}
} 

@inproceedings{Socher-etal:2013,
  Location = {Seattle, WA},
  Author = {Socher, Richard  and  Perelygin, Alex  and  Wu, Jean  and  Chuang, Jason  and  Manning, Christopher D.  and  Ng, Andrew Y.  and  Potts, Christopher},
  Booktitle = {Proceedings of the 2013 Conference on {E}mpirical {M}ethods in {N}atural {L}anguage {P}rocessing},
  Month = {October},
  Publisher = {Association for Computational Linguistics},
  Address = {Stroudsburg, PA},
  Title = {Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank},
  Pages = {1631--1642},
  Year = {2013}}
  
  @inproceedings{conf/icml/Martens10,
  author = {Martens, James},
  booktitle = {ICML},
  editor = {Fürnkranz, Johannes and Joachims, Thorsten},
  ee = {http://www.icml2010.org/papers/458.pdf},
  interhash = {1d6577ca73270732c2cc1e3c2cce6cdb},
  intrahash = {af0029f21446a26c04f2e4650ec1fbf1},
  keywords = {machinelearning neural-networks optimisation recurrent-neural-networks},
  pages = {735-742},
  publisher = {Omnipress},
  timestamp = {2011-07-08T14:11:15.000+0200},
  title = {Deep learning via Hessian-free optimization.},
  url = {http://dblp.uni-trier.de/db/conf/icml/icml2010.html#Martens10},
  year = 2010
}

@INPROCEEDINGS{Riedmiller93adirect,
    author = {Martin Riedmiller and Heinrich Braun},
    title = {A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm},
    booktitle = {IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS},
    year = {1993},
    pages = {586--591},
    publisher = {}
}
@article{Duchi:2011:ASM:1953048.2021068,
 author = {Duchi, John and Hazan, Elad and Singer, Yoram},
 title = {Adaptive Subgradient Methods for Online Learning and Stochastic Optimization},
 journal = {J. Mach. Learn. Res.},
 issue_date = {2/1/2011},
 volume = {12},
 month = jul,
 year = {2011},
 issn = {1532-4435},
 pages = {2121--2159},
 numpages = {39},
 url = {http://dl.acm.org/citation.cfm?id=1953048.2021068},
 acmid = {2021068},
 publisher = {JMLR.org}
} 

@INPROCEEDINGS{Prechelt97earlystopping,
    author = {Lutz Prechelt},
    title = {Early Stopping - but when?},
    booktitle = {Neural Networks: Tricks of the Trade, volume 1524 of LNCS, chapter 2},
    year = {1997},
    pages = {55--69},
    publisher = {Springer-Verlag}
}