bibliography.bib

@misc{graves2014neural,
  Author = {Alex Graves and Greg Wayne and Ivo Danihelka},
  Title = {Neural Turing Machines},
  Year = {2014},
  Eprint = {arXiv:1410.5401},
}

@misc{weston2014memory,
  Author = {Jason Weston and Sumit Chopra and Antoine Bordes},
  Title = {Memory Networks},
  Year = {2014},
  Eprint = {arXiv:1410.3916},
}

@misc{zaremba2014execute,
  Author = {Wojciech Zaremba and Ilya Sutskever},
  Title = {Learning to Execute},
  Year = {2014},
  Eprint = {arXiv:1410.4615},
}

@inproceedings{krizhevsky2012imagenet,
  title={Imagenet classification with deep convolutional neural networks},
  author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
  booktitle={Advances in neural information processing systems},
  pages={1097--1105},
  year={2012}
}

@inproceedings{bengio2013advances,
  title={Advances in optimizing recurrent networks},
  author={Bengio, Yoshua and Boulanger-Lewandowski, Nicolas and Pascanu, Razvan},
  booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on},
  pages={8624--8628},
  year={2013},
  organization={IEEE}
}

@inproceedings{martens2010deep,
  title={Deep learning via Hessian-free optimization},
  author={Martens, James},
  booktitle={Proceedings of the 27th International Conference on Machine Learning (ICML-10)},
  pages={735--742},
  year={2010}
}

@article{mou2014building,
  title={Building Program Vector Representations for Deep Learning},
  author={Mou, Lili and Li, Ge and Liu, Yuxuan and Peng, Hao and Jin, Zhi and Xu, Yan and Zhang, Lu},
  journal={arXiv preprint arXiv:1409.3358},
  year={2014}
}

@article{maddison2014structured,
  title={Structured Generative Models of Natural Source Code},
  author={Maddison, Chris J and Tarlow, Daniel},
  journal={arXiv preprint arXiv:1401.0514},
  year={2014}
}

@article{sutskever2014sequence,
  title={Sequence to Sequence Learning with Neural Networks},
  author={Sutskever, Ilya and Vinyals, Oriol and Le, Quoc V},
  journal={arXiv preprint arXiv:1409.3215},
  year={2014}
}

@article{bowman2013can,
  title={Can recursive neural tensor networks learn logical reasoning?},
  author={Bowman, Samuel R},
  journal={arXiv preprint arXiv:1312.6192},
  year={2013}
}

@article{bowman2014recursive,
  title={Recursive Neural Networks for Learning Logical Semantics},
  author={Bowman, Samuel R and Potts, Christopher and Manning, Christopher D},
  journal={arXiv preprint arXiv:1406.1827},
  year={2014}
}

@article{zaremba2014learning,
  title={Learning to Discover Efficient Mathematical Identities},
  author={Zaremba, Wojciech and Kurach, Karol and Fergus, Rob},
  journal={arXiv preprint arXiv:1406.1584},
  year={2014}
}


@inproceedings{lee2011learning,
  title={Learning the easy things first: Self-paced visual category discovery},
  author={Lee, Yong Jae and Grauman, Kristen},
  booktitle={Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on},
  pages={1721--1728},
  year={2011},
  organization={IEEE}
}

@inproceedings{kumar2010self,
  title={Self-paced learning for latent variable models},
  author={Kumar, M Pawan and Packer, Benjamin and Koller, Daphne},
  booktitle={Advances in Neural Information Processing Systems},
  pages={1189--1197},
  year={2010}
}

@inproceedings{bengio2009curriculum,
  title={Curriculum learning},
  author={Bengio, Yoshua and Louradour, J{\'e}r{\^o}me and Collobert, Ronan and Weston, Jason},
  booktitle={Proceedings of the 26th annual international conference on machine learning},
  pages={41--48},
  year={2009},
  organization={ACM}
}

@article{pham2013dropout,
  title={Dropout improves Recurrent Neural Networks for Handwriting Recognition},
  author={Pham, Vu and Kermorvant, Christopher and Louradour, J{\'e}r{\^o}me},
  journal={arXiv preprint arXiv:1312.4569},
  year={2013}
}

@article{zaremba2014recurrent,
  title={Recurrent Neural Network Regularization},
  author={Zaremba, Wojciech and Sutskever, Ilya and Vinyals, Oriol},
  journal={arXiv preprint arXiv:1409.2329},
  year={2014}
}

@incollection{wineberg1994representation,
  title={A representation scheme to perform program induction in a canonical genetic algorithm},
  author={Wineberg, Mark and Oppacher, Franz},
  booktitle={Parallel Problem Solving from Nature—PPSN III},
  pages={291--301},
  year={1994},
  publisher={Springer}
}

@book{nordin1997evolutionary,
  title={Evolutionary program induction of binary machine code and its applications},
  author={Nordin, Peter},
  year={1997},
  publisher={Krehl Munster}
}

@inproceedings{mikolov2012context,
  title={Context dependent recurrent neural network language model.},
  author={Mikolov, Tomas and Zweig, Geoffrey},
  booktitle={SLT},
  pages={234--239},
  year={2012}
}

@inproceedings{chow1987byblos,
  title={BYBLOS: The BBN continuous speech recognition system},
  author={Chow, Y and Dunham, M and Kimball, O and Krasner, M and Kubala, G and Makhoul, J and Price, P and Roucos, S and Schwartz, R},
  booktitle={Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'87.},
  volume={12},
  pages={89--92},
  year={1987},
  organization={IEEE}
}

@article{mikolov2013exploiting,
  title={Exploiting similarities among languages for machine translation},
  author={Mikolov, Tomas and Le, Quoc V and Sutskever, Ilya},
  journal={arXiv preprint arXiv:1309.4168},
  year={2013}
}

@article{marcus1993building,
  title={Building a large annotated corpus of English: The Penn Treebank},
  author={Marcus, Mitchell P and Marcinkiewicz, Mary Ann and Santorini, Beatrice},
  journal={Computational linguistics},
  volume={19},
  number={2},
  pages={313--330},
  year={1993},
  publisher={MIT Press}
}

@article{jaeger2007optimization,
  title={Optimization and applications of echo state networks with leaky-integrator neurons},
  author={Jaeger, Herbert and Luko{\v{s}}evi{\v{c}}ius, Mantas and Popovici, Dan and Siewert, Udo},
  journal={Neural Networks},
  volume={20},
  number={3},
  pages={335--352},
  year={2007},
  publisher={Elsevier}
}

@article{koutnik2014clockwork,
  title={A Clockwork RNN},
  author={Koutn{\'\i}k, Jan and Greff, Klaus and Gomez, Faustino and Schmidhuber, J{\"u}rgen},
  journal={arXiv preprint arXiv:1402.3511},
  year={2014}
}


@article{chenglanguage,
  title={Language Modeling with Sum-Product Networks},
  author={Cheng, Wei-Chen and Kok, Stanley and Pham, Hoai Vu and Chieu, Hai Leong and Chai, Kian Ming A}
}

@article{bayer2013fast,
  title={On Fast Dropout and its Applicability to Recurrent Networks},
  author={Bayer, Justin and Osendorfer, Christian and Chen, Nutan and Urban, Sebastian and van der Smagt, Patrick},
  journal={arXiv preprint arXiv:1311.0701},
  year={2013}
}

@phdthesis{srivastava2013improving,
  title={Improving neural networks with dropout},
  author={Srivastava, Nitish},
  year={2013},
  school={University of Toronto}
}

@inproceedings{wan2013regularization,
  title={Regularization of neural networks using dropconnect},
  author={Wan, Li and Zeiler, Matthew and Zhang, Sixin and Cun, Yann L and Fergus, Rob},
  booktitle={Proceedings of the 30th International Conference on Machine Learning (ICML-13)},
  pages={1058--1066},
  year={2013}
}

@article{warde2013empirical,
  title={An empirical analysis of dropout in piecewise linear networks},
  author={Warde-Farley, David and Goodfellow, Ian J and Courville, Aaron and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1312.6197},
  year={2013}
}


@inproceedings{wang2013fast,
  title={Fast dropout training},
  author={Wang, Sida and Manning, Christopher},
  booktitle={Proceedings of the 30th International Conference on Machine Learning (ICML-13)},
  pages={118--126},
  year={2013}
}

@inproceedings{mikolov2011strategies,
  title={Strategies for training large scale neural network language models},
  author={Mikolov, Tomas and Deoras, Anoop and Povey, Daniel and Burget, Lukas and Cernocky, Jan},
  booktitle={Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE Workshop on},
  pages={196--201},
  year={2011},
  organization={IEEE}
}

@inproceedings{mikolov2010recurrent,
  title={Recurrent neural network based language model.},
  author={Mikolov, Tomas and Karafi{\'a}t, Martin and Burget, Lukas and Cernock{\`y}, Jan and Khudanpur, Sanjeev},
  booktitle={INTERSPEECH},
  pages={1045--1048},
  year={2010}
}

@inproceedings{graves2013speech,
  title={Speech recognition with deep recurrent neural networks},
  author={Graves, Alex and Mohamed, Abdel-rahman and Hinton, Geoffrey},
  booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on},
  pages={6645--6649},
  year={2013},
  organization={IEEE}
}

@incollection{robinson1996use,
  title={The use of recurrent neural networks in continuous speech recognition},
  author={Robinson, Tony and Hochberg, Mike and Renals, Steve},
  booktitle={Automatic speech and speaker recognition},
  pages={233--258},
  year={1996},
  publisher={Springer}
}

@article{graves2009novel,
  title={A novel connectionist system for unconstrained handwriting recognition},
  author={Graves, Alex and Liwicki, Marcus and Fern{\'a}ndez, Santiago and Bertolami, Roman and Bunke, Horst and Schmidhuber, J{\"u}rgen},
  journal={Pattern Analysis and Machine Intelligence, IEEE Transactions on},
  volume={31},
  number={5},
  pages={855--868},
  year={2009},
  publisher={IEEE}
}

@article{hochreiter1997long,
  title={Long short-term memory},
  author={Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
  journal={Neural computation},
  volume={9},
  number={8},
  pages={1735--1780},
  year={1997},
  publisher={MIT Press}
}

@article{pascanu2013construct,
  title={How to Construct Deep Recurrent Neural Networks},
  author={Pascanu, Razvan and Gulcehre, Caglar and Cho, Kyunghyun and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1312.6026},
  year={2013}
}

@article{cho2014learning,
  title={Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation},
  author={Cho, Kyunghyun and van Merrienboer, Bart and Gulcehre, Caglar and Bougares, Fethi and Schwenk, Holger and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1406.1078},
  year={2014}
}

@INPROCEEDINGS{bergstra+al:2010-scipy,
 author = {Bergstra, James and Breuleux, Olivier and Bastien, Fr{\'{e}}d{\'{e}}ric and Lamblin, Pascal and Pascanu, Razvan and Desjardins, Guillaume and Turian, Joseph and Warde-Farley, David and Bengio, Yoshua},
 month = jun,
 title = {Theano: a {CPU} and {GPU} Math Expression Compiler},
 booktitle = {Proceedings of the Python for Scientific Computing Conference ({SciPy})},
 year = {2010},
 location = {Austin, TX},
 note = {Oral Presentation},
}


@phdthesis{mikolov2012statistical,
  title={Statistical language models based on neural networks},
  author={Mikolov, Tom{\'a}{\v{s}}},
  year={2012},
  school={Ph. D. thesis, Brno University of Technology}
}

@phdthesis{sutskever2013training,
  title={Training Recurrent Neural Networks},
  author={Sutskever, Ilya},
  year={2013},
  school={University of Toronto}
}

@article{graves2013generating,
  title={Generating sequences with recurrent neural networks},
  author={Graves, Alex},
  journal={arXiv preprint arXiv:1308.0850},
  year={2013}
}

@article{hopfield1982neural,
  title={Neural networks and physical systems with emergent collective computational abilities},
  author={Hopfield, John J},
  journal={Proceedings of the national academy of sciences},
  volume={79},
  number={8},
  pages={2554--2558},
  year={1982},
  publisher={National Acad Sciences}
}

@article{hinton2006fast,
  title={A fast learning algorithm for deep belief nets},
  author={Hinton, Geoffrey E and Osindero, Simon and Teh, Yee-Whye},
  journal={Neural computation},
  volume={18},
  number={7},
  pages={1527--1554},
  year={2006},
  publisher={MIT Press}
}

@inproceedings{langley00,
 author    = {P. Langley},
 title     = {Crafting Papers on Machine Learning},
 year      = {2000},
 pages     = {1207--1216},
 editor    = {Pat Langley},
 booktitle     = {Proceedings of the 17th International Conference
              on Machine Learning (ICML 2000)},
 address   = {Stanford, CA},
 publisher = {Morgan Kaufmann}
}

@TechReport{mitchell80,
  author = 	 "T. M. Mitchell",
  title = 	 "The Need for Biases in Learning Generalizations",
  institution =  "Computer Science Department, Rutgers University",
  year = 	 "1980",
  address =	 "New Brunswick, MA",
}

@phdthesis{kearns89,
  author = {M. J. Kearns},
  title =  {Computational Complexity of Machine Learning},
  school = {Department of Computer Science, Harvard University},
  year =   {1989}
}

@Book{MachineLearningI,
  editor = 	 "R. S. Michalski and J. G. Carbonell and T.
		  M. Mitchell",
  title = 	 "Machine Learning: An Artificial Intelligence
		  Approach, Vol. I",
  publisher = 	 "Tioga",
  year = 	 "1983",
  address =	 "Palo Alto, CA"
}

@Book{DudaHart2nd,
  author =       "R. O. Duda and P. E. Hart and D. G. Stork",
  title =        "Pattern Classification",
  publisher =    "John Wiley and Sons",
  edition =      "2nd",
  year =         "2000"
}

@misc{anonymous,
  title= {Suppressed for Anonymity},
  author= {Author, N. N.},
  year= {2011},
}

@InCollection{Newell81,
  author =       "A. Newell and P. S. Rosenbloom",
  title =        "Mechanisms of Skill Acquisition and the Law of
                  Practice", 
  booktitle =    "Cognitive Skills and Their Acquisition",
  pages =        "1--51",
  publisher =    "Lawrence Erlbaum Associates, Inc.",
  year =         "1981",
  editor =       "J. R. Anderson",
  chapter =      "1",
  address =      "Hillsdale, NJ"
}


@Article{Samuel59,
  author = 	 "A. L. Samuel",
  title = 	 "Some Studies in Machine Learning Using the Game of
		  Checkers",
  journal =	 "IBM Journal of Research and Development",
  year =	 "1959",
  volume =	 "3",
  number =	 "3",
  pages =	 "211--229"
}

@inproceedings{sak2014speech,
  title={Sequence Discriminative Distributed Training of Long Short-Term Memory Recurrent Neural Networks},
  author={H. Sak and O. Vinyals and G. Heigold and A. Senior and E. McDermott and R. Monga and M. Mao},
  booktitle={Interspeech},
  year={2014},
}

@book{BourlardASR,
 author = {Bourlard, H. and Morgan, N.},
 title = {Connectionist Speech Recognition: A Hybrid Approach},
 year = {1993},
 publisher = {Kluwer Academic Publishers},
} 

@article{cho,
  title={Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation},
  author={Cho, Kyunghyun and van Merrienboer, Bart and Gulcehre, Caglar and Bougares, Fethi and Schwenk, Holger and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1406.1078},
  year={2014}
}

@inproceedings{lium,
  title={LIUM's SMT machine translation systems for WMT 2011},
  author={Schwenk, Holger and Lambert, Patrik and Barrault, Lo{\"\i}c and Servan, Christophe and Afli, Haithem and Abdul-Rauf, Sadaf and Shah, Kashif},
  booktitle={Proceedings of the Sixth Workshop on Statistical Machine Translation},
  pages={464--469},
  year={2011},
  organization={Association for Computational Linguistics}
}


@ONLINE{wmt_joint,
author = {Holger Schwenk},
title = {University Le Mans},
year = {2014},
note={\\
      \href{http://www-lium.univ-lemans.fr/~schwenk/cslm_joint_paper/}
     {\nolinkurl{http://www-lium.univ-lemans.fr/}}
     \\
     \href{http://www-lium.univ-lemans.fr/~schwenk/cslm_joint_paper/}
     {\nolinkurl{~schwenk/cslm_joint_paper/}}
},
}

@inproceedings{kal13,
  title={Recurrent Continuous Translation Models},
  year={2013},
  author={N. Kalchbrenner and P. Blunsom},
  booktitle={EMNLP}
}
@inproceedings{devlin14,
title="Fast and Robust Neural Network Joint Models for Statistical Machine Translation",
author="J. Devlin and R. Zbib and Z. Huang and T. Lamar and R. Schwartz and J. Makhoul",
year=2014,
booktitle="ACL"
}
@article{bog14,
  title={Neural Machine Translation by Jointly Learning to Align and Translate},
  author={D. Bahdanau and K. Cho and Y. Bengio},
  journal={arXiv preprint arXiv:1409.0473},
  year={2014}
}