nn.bib

@article{BreimanML94,
    author = {Breiman, Leo},
    title = {Bagging predictors},
    journal = {Mach. Learn.},
    volume = 24,
    number = 2,
    pages = {123--140},
    month = aug,
    year = 1996
}

@misc{Chen16,
    author = {Chen, Kevin K.},
    title = {The Upper Bound on Knots in Neural Networks},
    year = 2016,
    month = nov,
    howpublished = {arXiv:1611.09448}
}

@misc{Ciresan12,
    author = {Cire\c{s}an, Dan and Meier, Ueli and Schmidhuber, J\"urgen},
    title = {Multi-column Deep Neural Networks for Image Classification},
    month = feb,
    year = 2012,
    howpublished = {arXiv:1202.2745}
}

@inproceedings{ClevertICLR16,
    author = {Clevert, Djork-Arn\'e and Unterthiner, Thomas and Hochreiter, Sepp},
    title = {Fast and Accurate Deep Network Learning by {Exponential Linear Units (ELUs)}},
    booktitle = {Sixth International Conference on Learning Representations ({ICLR})},
    year = 2016,
    month = may,
    address = {San Juan, Puerto Rico}
}

@article{CybenkoMCSS89,
    author = {Cybenko, George},
    title = {Approximation by superpositions of a sigmoidal function},
    journal = {Math. Control Signals Syst.},
    volume = {2},
    number = {4},
    pages = {303--314},
    year = {1989}
}

@article{DuchJMLR11,
    author = {Duchi, John and Hazan, Elad and Singer, Yoram},
    title = {Adaptive subgradient methods for online learning and stochastic optimization},
    journal = {J. Mach. Learn. Res.},
    volume = 12,
    month = jul,
    year = 2011,
    pages = {2121--2159}
}

@article{FreundJCSS97,
    author = {Freund, Yoav and Schapire, Robert E.},
    title = {A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting},
    journal = {J. Comput. Syst. Sci.},
    volume = 55,
    number = 1,
    year = 1997,
    month = aug,
    pages = {119--139}
}

@inproceedings{GlorotAISTATS10,
    author = {Glorot, Xavier and Bengio, Yoshua},
    title = {Understanding the difficulty of training deep feedforward neural networks},
    booktitle = {Proceedings of the 13th International Conference on Artificial Intelligence and Statistics ({AISTATS})},
    year = 2010,
    adderss = {Sardinia, Italy},
    series = {J. Mach. Learn. Res.},
    volume = 9
}

@book{GoodfellowDL,
    author = {Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron},
    title = {{D}eep Learning},
    publisher = {MIT Press},
    note = {\blueurl{https://www.deeplearningbook.org}},
    year = 2016,
    source = {actual paper}
}

@misc{He15a,
    author = {He, Kayming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
    title = {Delving deep into rectifiers: {S}urpassing human-level performance on {ImageNet} classification},
    month = feb,
    year = 2015,
    howpublished = {arXiv:1512.01852}
}

@misc{He15b,
    author = {He, Kayming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
    title = {Deep residual learning for image recognition},
    month = dec,
    year = 2015,
    howpublished = {arXiv:1512.03385}
}

@inproceedings{HenrionNIPS17,
    author = {Henrion, Isaac},
    title = {Neural Message Passing for Jet Physics},
    booktitle = {Neural Information Processing Systems (NIPS) Workshop on Deep Learning for Physical Sciences},
    year = 2017,
    month = dec,
    address = {Long Beach, CA}
}

@article{HornikNN89,
    author = {Hornik, Kurt and Stinchcombe, Maxwell and White, Halber},
    title = {Multilayer feedforward networks are universal approximators},
    journal = {Neural Netw.},
    volume = {2},
    number = 5,
    pages = {359--366},
    year = {1989}
}

@article{HornikNN91,
    author = {Hornik, Kurt},
    title = {Approximation capabilities of multilayer feedforward networks},
    journal = {Neural Netw.},
    volume = {4},
    number = {2},
    pages = {251--257},
    year = {1991}
}

@inproceedings{IoffeICML15,
    author = {Ioffe, Sergey and Szegedy, Christian},
    title = {Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift},
    booktitle = {Proceedings of the 32nd International Conference on Machine Learning ({ICML})},
    series = {Proc. Mach. Learn. Res.},
    volume = 37,
    address = {Lille, France},
    month = jul,
    year = 2015,
    pages = {448--456}
}

@inproceedings{KarpatneNIPS17,
    author = {Karpatne, Anuj},
    title = {Neural Message Passing for Jet Physics},
    booktitle = {Neural Information Processing Systems (NIPS) Workshop on Deep Learning for Physical Sciences},
    year = 2017,
    month = dec,
    address = {Long Beach, CA}
}

@inproceedings{KingmaICLR15,
    author = {Kingma, Diederik P. and Ba, Jimmy},
    title = {Adam: {A} method for stochastic optimization},
    booktitle = {Proceedings of the 3rd International Conference for Learning Representations ({ICLR})},
    address = {San Diego, CA},
    year = 2015,
    month = may
}

@inproceedings{KrizhevskyNIPS12,
    author = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E.},
    title = {Image{N}et Classification with Deep Convolutional Neural Networks},
    booktitle = {Advances in Neural Information Processing Systems},
    volume = {25},
    year = 2012,
    month = dec,
    address = {Lake Tahoe, NV}
}

@article{LeCunIEEE98,
    author = {LeCun, Yann and Bottou, L\'eon and Bengio, Yoshua and Haffner, Patrick},
    title = {Gradient-based learning applied to document recognition},
    journal = {Proc. IEEE},
    month = nov,
    year = 1998,
    volume = 86,
    number = 11
}

@inproceedings{MaasICML13,
    author = {Maas, Andrew L. and Hannun, Awni Y. and Ng, Andrew, Y.},
    title = {Rectifier nonlinearities improve neural network acoustic models},
    booktitle = {Proceedings of the 30th International Conference on Machine Learning ({ICML})},
    series = {Proc. Mach. Learn. Res.},
    volume = 28,
    year = 2013,
    month = jun,
    address = {Atlanta, GA}
}

@inproceedings{MontufarNIPS14,
    author = {Mont\'ufar, Guido and Pascanu, Razvan and Cho, Kyunghyun and Bengio, Yoshua},
    title = {On the number of linear regions of deep neural networks},
    booktitle = {Advances in Neural Information Processing Systems ({NIPS})},
    year = {2014},
    month = dec,
    address = {Montr\'eal, QC, Canada},
    pages = {2924--2932}
}

@misc{Pascanu13,
    author = {Pascanu, R. and Mont\'ufar, G. and Bengio, Y.},
    title = {On the number of response regions of deep feedforward networks with piecewise linear activations},
    note = {arXiv:1312.6098},
    month = dec,
    year = {2013}
}

@inbook{PressNR,
    author = {Press, William H. and Teukolsky, Saul A. and Vetterling, William T. and Flannery, Brian P.},
    title = {Numerical Recipes: The Art of Scientific Computing},
    edition = {3rd},
    year = 2007,
    chapter = 10,
    publisher = {Cambridge University Press},
    address = {New York, NY}
}

@inproceedings{RaghuICML17,
    author = {Raghu, Maithra and Poole, Ben and Kleinberg, Jon and Ganguli, Surya and Dickstein, Jascha S.},
    title = {On the expressive power of deep neural networks},
    booktitle = {Proceedings of the 34th International Conference on Machine Learning ({ICML})},
    series = {Proc. Mach. Learn. Res.},
    volume = 70,
    year = 2017,
    month = aug,
    address = {Sydney, Australia}
}

@inproceedings{RanzatoAISTATS10,
    author = {Ranzato, Marc'Aurelio and Krizhevsky, Alex and Hinton, Geoffrey E.},
    title = {Factored 3-way {B}oltzmann machines for modeling natural images},
    booktitle = {Proceedings of the 13th International Conference on Artificial Intelligence and Statistics ({AISTATS})},
    year = 2010,
    adderss = {Sardinia, Italy},
    series = {J. Mach. Learn. Res.},
    volume = 9
}

@misc{Real18,
    author = {Real, Esteban and Aggarwal, Alok and Huang, Yanping and Le, Quoc V.},
    title = {Regularized evolution for image classifier architecture search},
    month = feb,
    year = 2018,
    howpublished = {arXiv:1802.01548}
}

@techreport{RosenblattCornell57,
    author = {Rosenblatt, Frank},
    title = {The Perceptron--a perceiving and recognizing automaton},
    year = 1957,
    institution = {Cornell Aeronautical Laboratory},
    number = {85-460-1}
}

@article{RumelhartNature86,
    author = {Rumelhart, David E. and Hinton, Geoffrey E. and Williams, Ronald J.},
    title = {Learning representations by back-propagating errors},
    journal = {Nature},
    volume = 323,
    month = oct,
    year = 1986,
    pages = {533--536}
}

@article{SietsmaNN91,
    author = {Sietsma, Jocelyn and Dow, Robert J. F.},
    title = {Creating artificial neural networks that generalize},
    journal = {Neural Netw.},
    volume = 4,
    number = 1,
    year = 1991,
    pages = {67--79},
}

@misc{Simonyan14,
    author = {Simonyan, Karen and Zisserman, Andrew},
    title = {Very Deep Convolutional Networks for Large-Scale Image Recognition},
    month = sep,
    year = 2014,
    howpublished = {arXiv:1409.1556}
}

@inproceedings{SmithNIPS17,
    author = {Smith, Samuel L. and Kindermans, Pieter-Jan and Le, Quoc V.},
    title = {Don't Decay the Learning Rate, Increase the Batch Size},
    booktitle = {In Neural Information Processing Systems (NIPS) Workshop on Deep Learning: Bridging Theory and Practice},
    month = dec,
    year = 2017,
    address = {Long Beach, CA}
}

@article{SonodaACHA,
    author = {Sonoda, Sho and Murata, Noboru},
    title = {Neural network with unbounded activation functions is universal approximator},
    journal = {Appl. Comput. Harmon. Anal.},
    year = {2017},
    month = sep,
    volume = 43,
    number = 2,
    pages = {233--268}
}

@article{SrivastavaJMLR14,
    author = {Srivastava, Nitish and Hinton, Geoffrey and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
    title = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
    journal = {J. Mach. Learn. Res.},
    volume = 15,
    pages = {1929--1958},
    year = 2014,
    month = jun
}

@inproceedings{SzegedyIEEECVPR15,
    author = {Szegedy, Christian and Liu, Wei and Jia, Yangqing and Sermanet, Pierre and Reed, Scott and Anguelov, Dragomir and Erhan, Dumitru and Vanhoucke, Vincent and Rabinovich, Andrew},
    title = {Going deeper with convolutions},
    booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    month = jun,
    year = 2015,
    pages = {1--9},
    address = {Boston, MA}
}

@misc{TielemanRMSProp,
    author = {Tieleman, Tijmen and Hinton, Geoffrey E.},
    title = {Lecture 6e: rmsprop: {D}ivide the gradient by a running average of its recent magnitude},
    year = {2012}
}

@inproceedings{WanICML13,
    author = {Wan, Li and Zeiler, Matthew and Zhang, Sixin and LeCun, Yann and Fergus, Rob},
    title = {Regularization of Neural Networks using DropConnect},
    booktitle = {Proceedings of the 30th International Conference on Machine Learning ({ICML})},
    year = 2013,
    series = {Proceedings of Machine Learning Research},
    volume = 28,
    pages = {1058--1066},
    month = jun,
    address = {Atlanta, GA}
}

@inproceedings{WellingNIPS17,
    author = {Welling, Max},
    title = {Deep recurrent inverse modeling for radio astronomy and fast MRI imaging},
    booktitle = {Neural Information Processing Systems (NIPS) Workshop on Deep Learning for Physical Sciences},
    year = 2017,
    month = dec,
    address = {Long Beach, CA}
}

@misc{Zeiler12,
    author = {Zeiler, Matthew D.},
    title = {{ADADELTA}: {A}n adaptive learning rate method},
    month = dec,
    year = 2012,
    howpublished = {arXiv:1212.5701}
}

@inproceedings{ZeilerECCV14,
    author = {Zeiler, Matthew D. and Fergus, Rob},
    title = {Visualizing and understanding convolutional networks},
    booktitle = {Proceedings of the 13th European Conference on Computer Vision ({ECCV})},
    month = sep,
    year = 2014,
    address = {Zurich, Switzerland},
    pages = {818--833},
    series = {Lecture Notes in Computer Science},
    volume = 8689,
    publisher = {Springer},
    part = {I}
}