ReferencesKrizhevsky, A., Sutskever, I. & Hinton, G. ImageNet classification with deep convolutional neural networks. In Proc. Advances in Neural Information Processing Systems 25 1090–1098 (2012). This report was a breakthrough that used convolutional nets to almost halve the error rate for object recognition, and precipitated the rapid adoption of deep learning by the computer vision community. Google Scholar  Farabet, C., Couprie, C., Najman, L. & LeCun, Y. Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1915–1929 (2013).PubMed  Google Scholar  Tompson, J., Jain, A., LeCun, Y. & Bregler, C. Joint training of a convolutional network and a graphical model for human pose estimation. In Proc. Advances in Neural Information Processing Systems 27 1799–1807 (2014). Google Scholar  Szegedy, C. et al. Going deeper with convolutions. Preprint at http://arxiv.org/abs/1409.4842 (2014).Mikolov, T., Deoras, A., Povey, D., Burget, L. & Cernocky, J. Strategies for training large scale neural network language models. In Proc. Automatic Speech Recognition and Understanding 196–201 (2011). Google Scholar  Hinton, G. et al. Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Processing Magazine 29, 82–97 (2012). This joint paper from the major speech recognition laboratories, summarizing the breakthrough achieved with deep learning on the task of phonetic classification for automatic speech recognition, was the first major industrial application of deep learning.ADS  Google Scholar  Sainath, T., Mohamed, A.-R., Kingsbury, B. & Ramabhadran, B. Deep convolutional neural networks for LVCSR. In Proc. Acoustics, Speech and Signal Processing 8614–8618 (2013). Google Scholar  Ma, J., Sheridan, R. P., Liaw, A., Dahl, G. E. & Svetnik, V. Deep neural nets as a method for quantitative structure-activity relationships. J. Chem. Inf. Model. 55, 263–274 (2015).CAS  PubMed  Google Scholar  Ciodaro, T., Deva, D., de Seixas, J. & Damazio, D. Online particle detection with neural networks based on topological calorimetry information. J. Phys. Conf. Series 368, 012030 (2012). Google Scholar  Kaggle. Higgs boson machine learning challenge. Kaggle https://www.kaggle.com/c/higgs-boson (2014).Helmstaedter, M. et al. Connectomic reconstruction of the inner plexiform layer in the mouse retina. Nature 500, 168–174 (2013).ADS  CAS  PubMed  Google Scholar  Leung, M. K., Xiong, H. Y., Lee, L. J. & Frey, B. J. Deep learning of the tissue-regulated splicing code. Bioinformatics 30, i121–i129 (2014).CAS  PubMed  PubMed Central  Google Scholar  Xiong, H. Y. et al. The human splicing code reveals new insights into the genetic determinants of disease. Science 347, 6218 (2015). Google Scholar  Collobert, R., et al. Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493–2537 (2011).MATH  Google Scholar  Bordes, A., Chopra, S. & Weston, J. Question answering with subgraph embeddings. In Proc. Empirical Methods in Natural Language Processing http://arxiv.org/abs/1406.3676v3 (2014). Google Scholar  Jean, S., Cho, K., Memisevic, R. & Bengio, Y. On using very large target vocabulary for neural machine translation. In Proc. ACL-IJCNLP http://arxiv.org/abs/1412.2007 (2015). Google Scholar  Sutskever, I. Vinyals, O. & Le. Q. V. Sequence to sequence learning with neural networks. In Proc. Advances in Neural Information Processing Systems 27 3104–3112 (2014). This paper showed state-of-the-art machine translation results with the architecture introduced in ref. 72, with a recurrent network trained to read a sentence in one language, produce a semantic representation of its meaning, and generate a translation in another language. Google Scholar  Bottou, L. & Bousquet, O. The tradeoffs of large scale learning. In Proc. Advances in Neural Information Processing Systems 20 161–168 (2007). Google Scholar  Duda, R. O. & Hart, P. E. Pattern Classification and Scene Analysis (Wiley, 1973).MATH  Google Scholar  Schölkopf, B. & Smola, A. Learning with Kernels (MIT Press, 2002).MATH  Google Scholar  Bengio, Y., Delalleau, O. & Le Roux, N. The curse of highly variable functions for local kernel machines. In Proc. Advances in Neural Information Processing Systems 18 107–114 (2005). Google Scholar  Selfridge, O. G. Pandemonium: a paradigm for learning in mechanisation of thought processes. In Proc. Symposium on Mechanisation of Thought Processes 513–526 (1958). Google Scholar  Rosenblatt, F. The Perceptron — A Perceiving and Recognizing Automaton. Tech. Rep. 85-460-1 (Cornell Aeronautical Laboratory, 1957). Google Scholar  Werbos, P. Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. PhD thesis, Harvard Univ. (1974). Google Scholar  Parker, D. B. Learning Logic Report TR–47 (MIT Press, 1985). Google Scholar  LeCun, Y. Une procédure d'apprentissage pour Réseau à seuil assymétrique in Cognitiva 85: a la Frontière de l'Intelligence Artificielle, des Sciences de la Connaissance et des Neurosciences [in French] 599–604 (1985). Google Scholar  Rumelhart, D. E., Hinton, G. E. & Williams, R. J. Learning representations by back-propagating errors. Nature 323, 533–536 (1986).ADS  MATH  Google Scholar  Glorot, X., Bordes, A. & Bengio. Y. Deep sparse rectifier neural networks. In Proc. 14th International Conference on Artificial Intelligence and Statistics 315–323 (2011). This paper showed that supervised training of very deep neural networks is much faster if the hidden layers are composed of ReLU. Google Scholar  Dauphin, Y. et al. Identifying and attacking the saddle point problem in high-dimensional non-convex optimization. In Proc. Advances in Neural Information Processing Systems 27 2933–2941 (2014). Google Scholar  Choromanska, A., Henaff, M., Mathieu, M., Arous, G. B. & LeCun, Y. The loss surface of multilayer networks. In Proc. Conference on AI and Statistics http://arxiv.org/abs/1412.0233 (2014). Google Scholar  Hinton, G. E. What kind of graphical model is the brain? In Proc. 19th International Joint Conference on Artificial intelligence 1765–1775 (2005). Google Scholar  Hinton, G. E., Osindero, S. & Teh, Y.-W. A fast learning algorithm for deep belief nets. Neural Comp. 18, 1527–1554 (2006). This paper introduced a novel and effective way of training very deep neural networks by pre-training one hidden layer at a time using the unsupervised learning procedure for restricted Boltzmann machines.MathSciNet  MATH  Google Scholar  Bengio, Y., Lamblin, P., Popovici, D. & Larochelle, H. Greedy layer-wise training of deep networks. In Proc. Advances in Neural Information Processing Systems 19 153–160 (2006). This report demonstrated that the unsupervised pre-training method introduced in ref. 32 significantly improves performance on test data and generalizes the method to other unsupervised representation-learning techniques, such as auto-encoders.Ranzato, M., Poultney, C., Chopra, S. & LeCun, Y. Efficient learning of sparse representations with an energy-based model. In Proc. Advances in Neural Information Processing Systems 19 1137–1144 (2006). Google Scholar  Hinton, G. E. & Salakhutdinov, R. Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006).ADS  MathSciNet  CAS  PubMed  PubMed Central  MATH  Google Scholar  Sermanet, P., Kavukcuoglu, K., Chintala, S. & LeCun, Y. Pedestrian detection with unsupervised multi-stage feature learning. In Proc. International Conference on Computer Vision and Pattern Recognition http://arxiv.org/abs/1212.0142 (2013). Google Scholar  Raina, R., Madhavan, A. & Ng, A. Y. Large-scale deep unsupervised learning using graphics processors. In Proc. 26th Annual International Conference on Machine Learning 873–880 (2009). Google Scholar  Mohamed, A.-R., Dahl, G. E. & Hinton, G. Acoustic modeling using deep belief networks. IEEE Trans. Audio Speech Lang. Process. 20, 14–22 (2012). Google Scholar  Dahl, G. E., Yu, D., Deng, L. & Acero, A. Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20, 33–42 (2012). Google Scholar  Bengio, Y., Courville, A. & Vincent, P. Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Machine Intell. 35, 1798–1828 (2013). Google Scholar  LeCun, Y. et al. Handwritten digit recognition with a back-propagation network. In Proc. Advances in Neural Information Processing Systems 396–404 (1990). This is the first paper on convolutional networks trained by backpropagation for the task of classifying low-resolution images of handwritten digits. Google Scholar  LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998). This overview paper on the principles of end-to-end training of modular systems such as deep neural networks using gradient-based optimization showed how neural networks (and in particular convolutional nets) can be combined with search or inference mechanisms to model complex outputs that are interdependent, such as sequences of characters associated with the content of a document. Google Scholar  Hubel, D. H. & Wiesel, T. N. Receptive fields, binocular interaction, and functional architecture in the cat's visual cortex. J. Physiol. 160, 106–154 (1962).CAS  PubMed  PubMed Central  Google Scholar  Felleman, D. J. & Essen, D. C. V. Distributed hierarchical processing in the primate cerebral cortex. Cereb. Cortex 1, 1–47 (1991).CAS  PubMed  Google Scholar  Cadieu, C. F. et al. Deep neural networks rival the representation of primate it cortex for core visual object recognition. PLoS Comp. Biol. 10, e1003963 (2014). Google Scholar  Fukushima, K. & Miyake, S. Neocognitron: a new algorithm for pattern recognition tolerant of deformations and shifts in position. Pattern Recognition 15, 455–469 (1982). Google Scholar  Waibel, A., Hanazawa, T., Hinton, G. E., Shikano, K. & Lang, K. Phoneme recognition using time-delay neural networks. IEEE Trans. Acoustics Speech Signal Process. 37, 328–339 (1989). Google Scholar  Bottou, L., Fogelman-Soulié, F., Blanchet, P. & Lienard, J. Experiments with time delay networks and dynamic time warping for speaker independent isolated digit recognition. In Proc. EuroSpeech 89 537–540 (1989). Google Scholar  Simard, D., Steinkraus, P. Y. & Platt, J. C. Best practices for convolutional neural networks. In Proc. Document Analysis and Recognition 958–963 (2003). Google Scholar  Vaillant, R., Monrocq, C. & LeCun, Y. Original approach for the localisation of objects in images. In Proc. Vision, Image, and Signal Processing 141, 245–250 (1994). Google Scholar  Nowlan, S. & Platt, J. in Neural Information Processing Systems 901–908 (1995). Google Scholar  Lawrence, S., Giles, C. L., Tsoi, A. C. & Back, A. D. Face recognition: a convolutional neural-network approach. IEEE Trans. Neural Networks 8, 98–113 (1997).CAS  PubMed  Google Scholar  Ciresan, D., Meier, U. Masci, J. & Schmidhuber, J. Multi-column deep neural network for traffic sign classification. Neural Networks 32, 333–338 (2012).PubMed  Google Scholar  Ning, F. et al. Toward automatic phenotyping of developing embryos from videos. IEEE Trans. Image Process. 14, 1360–1371 (2005).ADS  PubMed  Google Scholar  Turaga, S. C. et al. Convolutional networks can learn to generate affinity graphs for image segmentation. Neural Comput. 22, 511–538 (2010).PubMed  MATH  Google Scholar  Garcia, C. & Delakis, M. Convolutional face finder: a neural architecture for fast and robust face detection. IEEE Trans. Pattern Anal. Machine Intell. 26, 1408–1423 (2004). Google Scholar  Osadchy, M., LeCun, Y. & Miller, M. Synergistic face detection and pose estimation with energy-based models. J. Mach. Learn. Res. 8, 1197–1215 (2007). Google Scholar  Tompson, J., Goroshin, R. R., Jain, A., LeCun, Y. Y. & Bregler, C. C. Efficient object localization using convolutional networks. In Proc. Conference on Computer Vision and Pattern Recognition http://arxiv.org/abs/1411.4280 (2014). Google Scholar  Taigman, Y., Yang, M., Ranzato, M. & Wolf, L. Deepface: closing the gap to human-level performance in face verification. In Proc. Conference on Computer Vision and Pattern Recognition 1701–1708 (2014). Google Scholar  Hadsell, R. et al. Learning long-range vision for autonomous off-road driving. J. Field Robot. 26, 120–144 (2009). Google Scholar  Farabet, C., Couprie, C., Najman, L. & LeCun, Y. Scene parsing with multiscale feature learning, purity trees, and optimal covers. In Proc. International Conference on Machine Learning http://arxiv.org/abs/1202.2160 (2012). Google Scholar  Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Machine Learning Res. 15, 1929–1958 (2014).MathSciNet  MATH  Google Scholar  Sermanet, P. et al. Overfeat: integrated recognition, localization and detection using convolutional networks. In Proc. International Conference on Learning Representations http://arxiv.org/abs/1312.6229 (2014). Google Scholar  Girshick, R., Donahue, J., Darrell, T. & Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proc. Conference on Computer Vision and Pattern Recognition 580–587 (2014). Google Scholar  Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. In Proc. International Conference on Learning Representations http://arxiv.org/abs/1409.1556 (2014). Google Scholar  Boser, B., Sackinger, E., Bromley, J., LeCun, Y. & Jackel, L. An analog neural network processor with programmable topology. J. Solid State Circuits 26, 2017–2025 (1991).ADS  Google Scholar  Farabet, C. et al. Large-scale FPGA-based convolutional networks. In Scaling up Machine Learning: Parallel and Distributed Approaches (eds Bekkerman, R., Bilenko, M. & Langford, J.) 399–419 (Cambridge Univ. Press, 2011). Google Scholar  Bengio, Y. Learning Deep Architectures for AI (Now, 2009).MATH  Google Scholar  Montufar, G. & Morton, J. When does a mixture of products contain a product of mixtures? J. Discrete Math. 29, 321–347 (2014).MathSciNet  MATH  Google Scholar  Montufar, G. F., Pascanu, R., Cho, K. & Bengio, Y. On the number of linear regions of deep neural networks. In Proc. Advances in Neural Information Processing Systems 27 2924–2932 (2014). Google Scholar  Bengio, Y., Ducharme, R. & Vincent, P. A neural probabilistic language model. In Proc. Advances in Neural Information Processing Systems 13 932–938 (2001). This paper introduced neural language models, which learn to convert a word symbol into a word vector or word embedding composed of learned semantic features in order to predict the next word in a sequence. Google Scholar  Cho, K. et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proc. Conference on Empirical Methods in Natural Language Processing 1724–1734 (2014). Google Scholar  Schwenk, H. Continuous space language models. Computer Speech Lang. 21, 492–518 (2007). Google Scholar  Socher, R., Lin, C. C-Y., Manning, C. & Ng, A. Y. Parsing natural scenes and natural language with recursive neural networks. In Proc. International Conference on Machine Learning 129–136 (2011). Google Scholar  Mikolov, T., Sutskever, I., Chen, K., Corrado, G. & Dean, J. Distributed representations of words and phrases and their compositionality. In Proc. Advances in Neural Information Processing Systems 26 3111–3119 (2013). Google Scholar  Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. In Proc. International Conference on Learning Representations http://arxiv.org/abs/1409.0473 (2015). Google Scholar  Hochreiter, S. Untersuchungen zu dynamischen neuronalen Netzen [in German] Diploma thesis, T.U. Münich (1991).Bengio, Y., Simard, P. & Frasconi, P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Networks 5, 157–166 (1994).CAS  PubMed  Google Scholar  Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735–1780 (1997). This paper introduced LSTM recurrent networks, which have become a crucial ingredient in recent advances with recurrent networks because they are good at learning long-range dependencies.CAS  PubMed  Google Scholar  ElHihi, S. & Bengio, Y. Hierarchical recurrent neural networks for long-term dependencies. In Proc. Advances in Neural Information Processing Systems 8 http://papers.nips.cc/paper/1102-hierarchical-recurrent-neural-networks-for-long-term-dependencies (1995). Google Scholar  Sutskever, I. Training Recurrent Neural Networks. PhD thesis, Univ. Toronto (2012). Google Scholar  Pascanu, R., Mikolov, T. & Bengio, Y. On the difficulty of training recurrent neural networks. In Proc. 30th International Conference on Machine Learning 1310–1318 (2013). Google Scholar  Sutskever, I., Martens, J. & Hinton, G. E. Generating text with recurrent neural networks. In Proc. 28th International Conference on Machine Learning 1017–1024 (2011). Google Scholar  Lakoff, G. & Johnson, M. Metaphors We Live By (Univ. Chicago Press, 2008). Google Scholar  Rogers, T. T. & McClelland, J. L. Semantic Cognition: A Parallel Distributed Processing Approach (MIT Press, 2004). Google Scholar  Xu, K. et al. Show, attend and tell: Neural image caption generation with visual attention. In Proc. International Conference on Learning Representations http://arxiv.org/abs/1502.03044 (2015). Google Scholar  Graves, A., Mohamed, A.-R. & Hinton, G. Speech recognition with deep recurrent neural networks. In Proc. International Conference on Acoustics, Speech and Signal Processing 6645–6649 (2013). Google Scholar  Graves, A., Wayne, G. & Danihelka, I. Neural Turing machines. http://arxiv.org/abs/1410.5401 (2014).Weston, J. Chopra, S. & Bordes, A. Memory networks. http://arxiv.org/abs/1410.3916 (2014).Weston, J., Bordes, A., Chopra, S. & Mikolov, T. Towards AI-complete question answering: a set of prerequisite toy tasks. http://arxiv.org/abs/1502.05698 (2015).Hinton, G. E., Dayan, P., Frey, B. J. & Neal, R. M. The wake-sleep algorithm for unsupervised neural networks. Science 268, 1558–1161 (1995). Google Scholar  Salakhutdinov, R. & Hinton, G. Deep Boltzmann machines. In Proc. International Conference on Artificial Intelligence and Statistics 448–455 (2009). Google Scholar  Vincent, P., Larochelle, H., Bengio, Y. & Manzagol, P.-A. Extracting and composing robust features with denoising autoencoders. In Proc. 25th International Conference on Machine Learning 1096–1103 (2008). Google Scholar  Kavukcuoglu, K. et al. Learning convolutional feature hierarchies for visual recognition. In Proc. Advances in Neural Information Processing Systems 23 1090–1098 (2010). Google Scholar  Gregor, K. & LeCun, Y. Learning fast approximations of sparse coding. In Proc. International Conference on Machine Learning 399–406 (2010). Google Scholar  Ranzato, M., Mnih, V., Susskind, J. M. & Hinton, G. E. Modeling natural images using gated MRFs. IEEE Trans. Pattern Anal. Machine Intell. 35, 2206–2222 (2013). Google Scholar  Bengio, Y., Thibodeau-Laufer, E., Alain, G. & Yosinski, J. Deep generative stochastic networks trainable by backprop. In Proc. 31st International Conference on Machine Learning 226–234 (2014). Google Scholar  Kingma, D., Rezende, D., Mohamed, S. & Welling, M. Semi-supervised learning with deep generative models. In Proc. Advances in Neural Information Processing Systems 27 3581–3589 (2014). Google Scholar  Ba, J., Mnih, V. & Kavukcuoglu, K. Multiple object recognition with visual attention. In Proc. International Conference on Learning Representations http://arxiv.org/abs/1412.7755 (2014). Google Scholar  Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015).ADS  CAS  PubMed  PubMed Central  Google Scholar  Bottou, L. From machine learning to machine reasoning. Mach. Learn. 94, 133–149 (2014).MathSciNet  Google Scholar  Vinyals, O., Toshev, A., Bengio, S. & Erhan, D. Show and tell: a neural image caption generator. In Proc. International Conference on Machine Learning http://arxiv.org/abs/1502.03044 (2014). Google Scholar  van der Maaten, L. & Hinton, G. E. Visualizing data using t-SNE. J. Mach. Learn.Research 9, 2579–2605 (2008).MATH  Google Scholar  Download references