How google's self-driving car works, IEEE Spectrum Online, pp.1132-1141, 2011. ,
ImageNet classification with deep convolutional neural networks, Advances in neural information processing systems, pp.1097-1105, 2012. ,
DOI : 10.1162/neco.2009.10-08-881
URL : http://dl.acm.org/ft_gateway.cfm?id=3065386&type=pdf
Generative adversarial nets, Advances in neural information processing systems, pp.2672-2680, 2014. ,
The era of cognitive systems: An inside look at IBM Watson and how it works, IBM Corporation ,
Where does AlphaGo go: From Church-Turing thesis to AlphaGo thesis and beyond, IEEE, pp.113-120, 2016. ,
Libratus: The Superhuman AI for No-Limit Poker, Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017. ,
DOI : 10.24963/ijcai.2017/772
Human-level artificial general intelligence and the possibility of a technological singularity, Artificial Intelligence, vol.171, issue.18 ,
DOI : 10.1016/j.artint.2007.10.011
, Dermott's critique of Kurzweil, In Artificial Intelligence, vol.171, issue.18, pp.1161-1173, 2007.
, 32001-20160617ARTFIG00317- yann-lecun-l-intelligence-artificielle-a-connu-des-succes-et-des-echecs, 2016.
Future Progress in Artificial Intelligence: A Survey of Expert Opinion, In Fundamental issues of artificial intelligence, vol.26, issue.3, pp.555-572, 2016. ,
DOI : 10.1080/0952813X.2014.895110
,
Non-Holographic Associative Memory, Nature, 1969. ,
DOI : 10.1038/222960a0
Learning algorithms for classification: A comparison on handwritten digit recognition, Neural networks: the statistical mechanics perspective, pp.261-276, 1995. ,
Neural networks and physical systems with emergent collective computational abilities, Proceedings of the national academy of sciences, pp.2554-2558, 1982. ,
Potts-glass models of neural networks, Physical Review A, vol.20, issue.7, p.2739, 1988. ,
DOI : 10.1088/0022-3719/20/13/008
Sparse Neural Networks With Large Learning Diversity, IEEE transactions on neural networks, pp.1087-1096 ,
DOI : 10.1109/TNN.2011.2146789
URL : https://hal.archives-ouvertes.fr/hal-00609246
The organization of behavior, 1949. ,
Analog Versus Digital: Extrapolating from Electronics to Neurobiology, Neural Computation, vol.72, issue.7, pp.1601-1638, 1998. ,
DOI : 10.1109/101.261888
Information, noise, coding, modulation: What about the brain?, 2014 8th International Symposium on Turbo Codes and Iterative Information Processing (ISTC), pp.167-172, 2014. ,
DOI : 10.1109/ISTC.2014.6955107
URL : https://hal.archives-ouvertes.fr/hal-01170344
Analog and digital codes in the brain, Physical Review E, vol.79, issue.2, p.22705, 2014. ,
DOI : 10.1007/s10827-009-0182-2
URL : http://arxiv.org/pdf/1311.4035
Network hubs in the human brain, Trends in cognitive sciences, pp.683-696, 2013. ,
DOI : 10.1016/j.tics.2013.09.012
The Human Thalamus Is an Integrative Hub for Functional Brain Networks, The Journal of Neuroscience, vol.37, issue.23, pp.5594-5607, 2017. ,
DOI : 10.1523/JNEUROSCI.0067-17.2017
URL : http://www.jneurosci.org/content/37/23/5594.full.pdf
A general framework for parallel distributed processing, Parallel distributed processing: Explorations in the microstructure of cognition, pp.45-76, 1986. ,
Development of the Brain depends on the Visual Environment, Nature, vol.56, issue.5270, pp.477-478, 1970. ,
DOI : 10.1113/jphysiol.1970.sp009022
Visual Experience Modifies Distribution of Horizontally and Vertically Oriented Receptive Fields in Cats, Science, vol.168, issue.3933, pp.869-871, 1970. ,
DOI : 10.1126/science.168.3933.869
When will computer hardware match the human brain, In Journal of evolution and technology, vol.1, issue.1, p.10, 1998. ,
A Nonvolatile Associative Memory-Based Context-Driven Search Engine Using 90 nm CMOS/MTJ-Hybrid Logic-in-Memory Architecture, IEEE Journal on Emerging and Selected Topics in Circuits and Systems, pp.460-474, 2014. ,
DOI : 10.1109/JETCAS.2014.2361061
URL : https://hal.archives-ouvertes.fr/hal-01172742
Low-power area-efficient large-scale IP lookup engine based on binary-weighted clustered networks, Proceedings of the 50th Annual Design Automation Conference on, DAC '13, pp.2013-55 ,
DOI : 10.1145/2463209.2488801
CAM-based VLSI architectures for dynamic Huffman coding, IEEE Trans. Consum. Electron, vol.40, issue.3, pp.282-289, 1994. ,
A Class of Sparsely Connected Autoassociative Morphological Memories for Large Color Images, IEEE Transactions on Neural Networks, vol.20, issue.6, pp.1045-1050, 2009. ,
DOI : 10.1109/TNN.2009.2020849
Automatic face recognition using SIFT and networks of tagged neural cliques, Proceedings of Cognitive, pp.57-61, 2015. ,
Speech processing in the auditory system II: Lateral inhibition and the central processing of speech evoked activity in the auditory nerve, The Journal of the Acoustical Society of America, vol.78, issue.5, pp.1622-1632, 1985. ,
DOI : 10.1121/1.392800
Inhibitory Stabilization of the Cortical Network Underlies Visual Surround Suppression, Neuron, vol.62, issue.4, pp.578-592, 2009. ,
DOI : 10.1016/j.neuron.2009.03.028
URL : http://www.neurotheory.columbia.edu/~ken/pubs/ozeki-etal09.pdf
Consecutive and non-consecutive heteroclinic cycles in Hopfield networks, Dynamical Systems, vol.32, issue.1, pp.1-15, 2016. ,
DOI : 10.1016/j.neuron.2008.12.032
URL : https://hal.archives-ouvertes.fr/hal-01654634
The capacity of the Hopfield associative memory, IEEE Transactions on Information Theory, vol.33, issue.4, pp.461-482, 1987. ,
DOI : 10.1109/TIT.1987.1057328
High-dimensional computing with sparse vectors, 2015 IEEE Biomedical Circuits and Systems Conference (BioCAS), pp.1-4, 2015. ,
DOI : 10.1109/BioCAS.2015.7348414
Theories of associative recall, Quarterly Reviews of Biophysics, vol.13, issue.02, pp.223-244, 1970. ,
DOI : 10.1037/h0042519
Comparison Between Kanerva's SDM and Hopfield-type Neural Networks, Cognitive Science, vol.222, issue.3, pp.299-329, 1988. ,
DOI : 10.1038/222960a0
URL : http://onlinelibrary.wiley.com/doi/10.1207/s15516709cog1203_1/pdf
Optimal Plasticity from Matrix Memories: What Goes Up Must Come Down, Neural Computation, vol.83, issue.1, pp.85-93, 1990. ,
DOI : 10.1209/0295-5075/6/2/002
Memory Capacities for Synaptic and Structural Plasticity, Neural Computation, vol.13, issue.1, pp.289-341, 2010. ,
DOI : 10.1002/(SICI)1097-4695(199610)31:2<219::AID-NEU7>3.0.CO;2-E
Clique-Based Neural Associative Memories with Local Coding and Precoding, Neural Computation, vol.28, issue.8, 2016. ,
DOI : 10.1038/222960a0
A simple and efficient way to store many messages using neural cliques, 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), pp.1-5, 2011. ,
DOI : 10.1109/CCMB.2011.5952106
URL : https://hal.archives-ouvertes.fr/hal-01056522
, Nearly-optimal associative memories based on distributed constant weight codes, Theory and Applications Workshop (ITA), 2012, pp.269-273
Storing Sparse Messages in Networks of Neural Cliques, Proceedings of the national academy of sciences, pp.461-482, 2014. ,
DOI : 10.1109/TNNLS.2013.2285253
URL : https://hal.archives-ouvertes.fr/hal-00994216
Neural associative memories and sparse coding, Neural Networks, vol.37, pp.165-171, 1987. ,
DOI : 10.1016/j.neunet.2012.08.013
Nature and Interaction of Signals From the Receptive Field Center and Surround in Macaque V1 Neurons, Journal of Neurophysiology, vol.40, issue.5, pp.2530-2546, 2002. ,
DOI : 10.1093/cercor/6.2.297
Psychology of touch and blindness, 2013. ,
The self-organizing map, Neurocomputing, vol.21, issue.1-3, pp.1-6, 1998. ,
DOI : 10.1016/S0925-2312(98)00030-7
A study of retrieval algorithms of sparse messages in networks of neural cliques, Proceedings of the Sixth International Conference on Advanced Cognitive Technologies and Applications, pp.140-146, 2014. ,
URL : https://hal.archives-ouvertes.fr/hal-01058303
Tree-based reparameterization framework for analysis of sum-product and related algorithms, IEEE Transactions on Information Theory, vol.49, issue.5, pp.1120-1146, 2003. ,
DOI : 10.1109/TIT.2003.810642
Receptive fields, binocular interaction and functional architecture in the cat's visual cortex, The Journal of Physiology, vol.160, issue.1, pp.106-154, 1962. ,
DOI : 10.1113/jphysiol.1962.sp006837
Receptive fields and functional architecture of monkey striate cortex, The Journal of Physiology, vol.195, issue.1, pp.215-243, 1968. ,
DOI : 10.1113/jphysiol.1968.sp008455
Minimum information required for written word recognition, Groupe de Linguistique Appliquée des Télécommunications (GLAT), pp.84-91, 2014. ,
URL : https://hal.archives-ouvertes.fr/hal-01222081
Visual recognition of partially displayed words ,
Perceptual recognition as a function of meaningfulness of stimulus material., Journal of Experimental Psychology, vol.81, issue.2, pp.275-280, 1969. ,
DOI : 10.1037/h0027768
Processes in word recognition, Cognitive Psychology, vol.1, issue.1, pp.59-85, 1970. ,
DOI : 10.1016/0010-0285(70)90005-8
A template matching model for pattern recognition: Self-organization of templates and template matching by a disinhibitory neural network, Biological Cybernetics, vol.201, issue.2, pp.91-101, 1980. ,
DOI : 10.1113/jphysiol.1975.sp011025
Recognition of handwritten digits using template and model matching, Pattern recognition, pp.421-431, 1991. ,
DOI : 10.1016/0031-3203(91)90055-A
Theory of Cognitive Pattern Recognition, Pattern Recognition Techniques, Technology and Applications. InTech, pp.433-463, 2008. ,
DOI : 10.5772/6251
URL : http://intechweb.org/downloadpdf.php?id=5795
An interactive activation model of context effects in letter perception: I. An account of basic findings., Psychological review, p.375, 1981. ,
DOI : 10.1037/0033-295X.88.5.375
Fast phonology and the Bimodal Interactive Activation Model, European Journal of Cognitive Psychology, vol.22, issue.5, pp.764-778, 2010. ,
DOI : 10.1080/016909698386555
URL : https://hal.archives-ouvertes.fr/hal-01440447
Orthographic Neighborhood Effects in Bilingual Word Recognition, Journal of Memory and Language, vol.39, issue.3, pp.458-483, 1998. ,
DOI : 10.1006/jmla.1998.2584
The architecture of the bilingual word recognition system: From identification to decision, Bilingualism: Language and Cognition, vol.5, issue.03, pp.175-197 ,
DOI : 10.1017/S1366728902003012
, , 1969.
Neocognitron, Scholarpedia, vol.2, issue.1, pp.59-69, 1980. ,
DOI : 10.4249/scholarpedia.1717
Approximation by superpositions of a sigmoidal function, Mathematics of Control, Signals, and Systems (MCSS), pp.303-314, 1989. ,
Visualizing and Understanding Convolutional Networks, European conference on computer vision, pp.818-833, 2014. ,
DOI : 10.1007/978-3-319-10590-1_53
Visualizing higher-layer features of a deep network, p.1341 ,
Understanding deep image representations by inverting them, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.5188-5196, 2015. ,
DOI : 10.1109/CVPR.2015.7299155
, Understanding neural networks through deep visualization, 2015.
Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition, PLoS Computational Biology, vol.29, issue.025, p.1003963, 2014. ,
DOI : 10.1371/journal.pcbi.1003963.s006
How Does the Brain Solve Visual Object Recognition?, Neuron, vol.73, issue.3, pp.415-434, 2012. ,
DOI : 10.1016/j.neuron.2012.01.010
Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition, In Neurocomputing, pp.227-236, 1990. ,
DOI : 10.1007/978-3-642-76153-9_28
The regression analysis of binary sequences, In Journal of the Royal Statistical Society. Series B (Methodological), pp.215-242, 1958. ,
A Biological Gradient Descent for Prediction Through a Combination of STDP and Homeostatic Plasticity, Neural Computation, vol.20, issue.23, pp.2815-2832, 2013. ,
DOI : 10.1103/PhysRevE.75.051917
URL : http://arxiv.org/pdf/1206.4812
Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network, Neural Computation, vol.1, issue.2, pp.441-454, 2003. ,
DOI : 10.1038/331679a0
URL : http://www.princeton.edu/~xhx/chl.pdf
Recurrent processing during object recognition Supporting Information, p.690 ,
Performance-optimized hierarchical models predict neural responses in higher visual cortex, Proceedings of the National Academy of Sciences, pp.8619-8624, 2014. ,
DOI : 10.1038/nn972
URL : http://www.pnas.org/content/111/23/8619.full.pdf
Learning deep architectures for AI Foundations and trends, Machine Learning, pp.1-127, 2009. ,
DOI : 10.1561/2200000006
URL : http://www.iro.umontreal.ca/~bengioy/papers/ftml.pdf
Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation, PLoS Computational Biology, vol.55, issue.14, p.1003915, 2014. ,
DOI : 10.1371/journal.pcbi.1003915.s014
URL : https://doi.org/10.1371/journal.pcbi.1003915
Origins of the specialization for letters and numbers in ventral occipitotemporal cortex, Trends in cognitive sciences, pp.374-382, 2015. ,
DOI : 10.1016/j.tics.2015.05.006
Rectified linear units improve restricted Boltzmann machines, Proceedings of the 27th international conference on machine learning (ICML-10), pp.807-814, 2010. ,
Improving neural networks by preventing co-adaptation of feature detectors, 2012. ,
Dropout: a simple way to prevent neural networks from overfitting, Journal of Machine Learning Research, vol.15, issue.1, pp.1929-1958, 2014. ,
Pattern recognition: A statistical approach, 1982. ,
Theano: new features and speed improvements, 2012. ,
, Keras: Theano-based deep learning library Code: https://github.com/fchollet, 2015.
The mathematical theory of communication, 1949. ,
Conditional likelihood maximisation: a unifying framework for information theoretic feature selection, In Journal of Machine Learning Research, vol.13, pp.27-66, 2012. ,
The use of film subtitles to estimate word frequencies, Applied psycholinguistics, pp.661-677, 2007. ,
DOI : 10.1080/01690960400023485
Visualizing data using t-SNE, In Journal of Machine Learning Research, vol.9, pp.2579-2605, 2008. ,
Reading Text in the Wild with Convolutional Neural Networks, International Journal of Computer Vision, vol.20, issue.9, pp.1-20, 2016. ,
DOI : 10.1109/TIP.2011.2126586
A connectionist model of reading with error correction properties, LTC 2015: 7th Language and Technology Conference, pp.455-460, 2015. ,
URL : https://hal.archives-ouvertes.fr/hal-01311631
Intriguing properties of neural networks," arXiv preprint arXiv:1312, p.6199, 2013. ,
, Chollet, https://blog.keras.io/how-convolutional-neural-networks-see-theworld .html, 2016.
One-Shot learning with a hierarchical nonparametric Bayesian model, ICML Unsupervised and Transfer Learning, pp.195-206, 2012. ,
Review of Classifier Combination Methods, Machine Learning in Document Analysis and Recognition, pp.361-386, 2008. ,
DOI : 10.1007/978-3-540-76280-5_14
Bayesian classifier combination, In Artificial Intelligence and Statistics, pp.619-627, 2008. ,
Dynamic Bayesian Combination of Multiple Imperfect Classifiers, Decision making and imperfection, pp.1-35, 2013. ,
DOI : 10.1007/978-3-642-36406-8_1
On the effect of calibration in classifier combination, Applied intelligence, pp.566-585, 2013. ,
DOI : 10.1145/775047.775151
Error correcting output codes for multiclass classification: Application to two image vision problems, The 16th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP 2012), pp.2012-508 ,
DOI : 10.1109/AISP.2012.6313800
Probabilistic interpretation of feed-forward classification network outputs, with relationships to statistical pattern recognition, In Neurocomputing, pp.227-236, 1990. ,
A Model Selection Algorithm for a Posteriori Probability Estimation With Neural Networks, IEEE Transactions on Neural Networks, pp.799-809, 2005. ,
DOI : 10.1109/TNN.2005.849826
The MNIST database of handwritten digits, 1998. ,
Deconstructing the ladder network architecture, International Conference on Machine Learning, pp.2368-2376, 2016. ,
Reading digits in natural images with unsupervised feature learning, NIPS workshop on deep learning and unsupervised feature learning, p.4, 2011. ,
Batch normalization: Accelerating deep network training by reducing internal covariate shift, 2015. ,
Adam: A method for stochastic optimization, 2014. ,
Theano: new features and speed improvements arXiv preprint arXiv: 1211.5590,2012. [108] F. Chollet Keras: Theano-based deep learning library Code: https://github.com/fchollet, 2015. ,
Lower bounds for constant weight codes, IEEE Transactions on Information Theory, pp.37-43, 1980. ,
DOI : 10.1109/TIT.1980.1056141
Development of cortical folding during evolution and ontogeny, Trends in neurosciences, pp.275-284, 2013. ,
DOI : 10.1016/j.tins.2013.01.006
Error Detecting and Error Correcting Codes, Bell System Technical Journal, vol.29, issue.2, pp.147-160, 1950. ,
DOI : 10.1002/j.1538-7305.1950.tb00463.x
Near optimum decoding of product codes, 1994 IEEE GLOBECOM. Communications: The Global Bridge, pp.339-343, 1994. ,
DOI : 10.1109/GLOCOM.1994.513494
Reading Text in the Wild with Convolutional Neural Networks, International Journal of Computer Vision, vol.20, issue.9, pp.1-20, 2016. ,
DOI : 10.1109/TIP.2011.2126586
URL : http://arxiv.org/pdf/1412.1842
Understanding the difficulty of training deep feedforward neural networks, In AIstats, vol.9, pp.249-256, 2010. ,
Analog implementation of encoded neural networks, 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013), pp.1612-1615, 2013. ,
DOI : 10.1109/ISCAS.2013.6572170
URL : https://hal.archives-ouvertes.fr/hal-00836649
A GPU-based associative memory using sparse Neural Networks, 2014 International Conference on High Performance Computing & Simulation (HPCS), p.2014 ,
DOI : 10.1109/HPCSim.2014.6903755
URL : https://hal.archives-ouvertes.fr/hal-01174294
, International Conference on, pp.688-692, 2014.
A massively parallel associative memory based on sparse neural networks, 2013. ,
Sum-product networks: A new deep architecture, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp.689-690, 2011. ,
DOI : 10.1109/ICCVW.2011.6130310
Shallow vs. deep sum-product networks, Advances in Neural Information Processing Systems, pp.666-674 ,
The perceptron: A probabilistic model for information storage and organization in the brain., Psychological review, p.386, 1958. ,
DOI : 10.1037/h0042519
Theano: Deep learning on GPUs with python, NIPS 2011 ,
Extracting and composing robust features with denoising autoencoders, Proceedings of the 25th international conference on Machine learning, ICML '08, pp.1096-1103, 2008. ,
DOI : 10.1145/1390156.1390294
Compete to compute, Advances in neural information processing systems, pp.2310-2318, 2013. ,
K-sparse autoencoders, 2013. ,
Some developmental and attentional biases in the contrast enhancement and short term memory of recurrent neural networks, Journal of Theoretical Biology, vol.53, issue.2, pp.341-380, 1975. ,
DOI : 10.1016/S0022-5193(75)80009-9
How do cell assemblies encode information in the brain?, Neuroscience & Biobehavioral Reviews, vol.23, issue.6, pp.785-796, 1999. ,
DOI : 10.1016/S0149-7634(99)00017-2
Direct Activation of Sparse, Distributed Populations of Cortical Neurons by Electrical Microstimulation, Neuron, vol.63, issue.4, pp.508-522, 2009. ,
DOI : 10.1016/j.neuron.2009.07.016
The Code for Facial Identity in the Primate Brain, Cell, vol.169, issue.6, pp.1013-1028, 2017. ,
DOI : 10.1016/j.cell.2017.05.011
Semi-supervised learning with ladder networks, Advances in Neural Information Processing Systems, pp.3546-3554, 2015. ,
Improved techniques for training GANs, Advances in Neural Information Processing Systems, pp.2234-2242, 2016. ,
Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks, Workshop on Challenges in Representation Learning, ICML, p.2, 2013. ,
Approximate computing: An emerging paradigm for energy-efficient design, 2013 18TH IEEE EUROPEAN TEST SYMPOSIUM (ETS), pp.1-6, 2013. ,
DOI : 10.1109/ETS.2013.6569370
On the use of aggregation operations in information fusion processes, Fuzzy sets and systems, pp.143-161, 2004. ,
DOI : 10.1016/j.fss.2003.10.038