generated by bibbase.org
  2013 (11)
Discovering Multiple Constraints that are Frequently Approximately Satisfied. Hinton, G. E.; and Teh, Y. W. CoRR, abs/1301.2278. 2013.
Discovering Multiple Constraints that are Frequently Approximately Satisfied [link] link   Discovering Multiple Constraints that are Frequently Approximately Satisfied [link] psgz   Discovering Multiple Constraints that are Frequently Approximately Satisfied [pdf] pdf   link   bibtex   3 downloads  
Modeling Documents with Deep Boltzmann Machines. Srivastava, N.; Salakhutdinov, R.; and Hinton, G. E. CoRR, abs/1309.6865. 2013.
Modeling Documents with Deep Boltzmann Machines [link] link   Modeling Documents with Deep Boltzmann Machines [pdf] pdf   link   bibtex   9 downloads  
Speech Recognition with Deep Recurrent Neural Networks. Graves, A.; Mohamed, A.; and Hinton, G. E. CoRR, abs/1303.5778. 2013.
Speech Recognition with Deep Recurrent Neural Networks [link] link   Speech Recognition with Deep Recurrent Neural Networks [pdf] pdf   link   bibtex   27 downloads  
On rectified linear units for speech processing. Zeiler, M. D.; Ranzato, M.; Monga, R.; Mao, M. Z.; Yang, K.; Le, Q. V.; Nguyen, P.; Senior, A. W.; Vanhoucke, V.; Dean, J.; and Hinton, G. E. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 3517-3521, 2013.
On rectified linear units for speech processing [link] link   On rectified linear units for speech processing [pdf] pdf   link   bibtex  
Speech recognition with deep recurrent neural networks. Graves, A.; Mohamed, A.; and Hinton, G. E. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 6645-6649, 2013.
Speech recognition with deep recurrent neural networks [link] link   Speech recognition with deep recurrent neural networks [pdf] pdf   link   bibtex   27 downloads  
New types of deep neural network learning for speech recognition and related applications: an overview. Deng, L.; Hinton, G. E.; and Kingsbury, B. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 8599-8603, 2013.
New types of deep neural network learning for speech recognition and related applications: an overview [link] link   New types of deep neural network learning for speech recognition and related applications: an overview [pdf] pdf   link   bibtex   5 downloads  
Improving deep neural networks for LVCSR using rectified linear units and dropout. Dahl, G. E.; Sainath, T. N.; and Hinton, G. E. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 8609-8613, 2013.
Improving deep neural networks for LVCSR using rectified linear units and dropout [link] link   Improving deep neural networks for LVCSR using rectified linear units and dropout [pdf] pdf   link   bibtex   4 downloads  
Tensor Analyzers. Tang, Y.; Salakhutdinov, R.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), pages 163-171, 2013.
Tensor Analyzers [link] link   Tensor Analyzers [pdf] pdf   link   bibtex   4 downloads  
On the importance of initialization and momentum in deep learning. Sutskever, I.; Martens, J.; Dahl, G. E.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), pages 1139-1147, 2013.
On the importance of initialization and momentum in deep learning [link] link   On the importance of initialization and momentum in deep learning [pdf] pdf   link   bibtex   2 downloads  
Modeling Natural Images Using Gated MRFs. Ranzato, M.; Mnih, V.; Susskind, J. M.; and Hinton, G. E. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI), 35(9): 2206-2222. 2013.
Modeling Natural Images Using Gated MRFs [link] link   Modeling Natural Images Using Gated MRFs [pdf] pdf   link   bibtex   4 downloads  
Using an autoencoder with deformable templates to discover features for automated speech recognition. Jaitly, N.; and Hinton, G. E. In Proceedings of Conference of the International Speech Communication Association (INTERSPEECH), pages 1737-1740, 2013.
Using an autoencoder with deformable templates to discover features for automated speech recognition [link] link   link   bibtex  
  2012 (18)
Robust Boltzmann Machines for recognition and denoising. Tang, Y.; Salakhutdinov, R.; and Hinton, G. E. In Proceedings of Computer Vision and Pattern Recognition (CVPR), pages 2264-2271, 2012.
Robust Boltzmann Machines for recognition and denoising [link] link   Robust Boltzmann Machines for recognition and denoising [pdf] pdf   link   bibtex   3 downloads  
Conditional Restricted Boltzmann Machines for Structured Output Prediction. Mnih, V.; Larochelle, H.; and Hinton, G. E. CoRR, abs/1202.3748. 2012.
Conditional Restricted Boltzmann Machines for Structured Output Prediction [link] link   Conditional Restricted Boltzmann Machines for Structured Output Prediction [pdf] pdf   link   bibtex  
Deep Mixtures of Factor Analysers. Tang, Y.; Salakhutdinov, R.; and Hinton, G. E. CoRR, abs/1206.4635. 2012.
Deep Mixtures of Factor Analysers [link] link   Deep Mixtures of Factor Analysers [pdf] pdf   link   bibtex   1 download  
Efficient Parametric Projection Pursuit Density Estimation. Welling, M.; Zemel, R. S.; and Hinton, G. E. CoRR, abs/1212.2513. 2012.
Efficient Parametric Projection Pursuit Density Estimation [link] link   Efficient Parametric Projection Pursuit Density Estimation [link] psgz   link   bibtex  
Improving neural networks by preventing co-adaptation of feature detectors. Hinton, G. E.; Srivastava, N.; Krizhevsky, A.; Sutskever, I.; and Salakhutdinov, R. CoRR, abs/1207.0580. 2012.
Improving neural networks by preventing co-adaptation of feature detectors [link] link   Improving neural networks by preventing co-adaptation of feature detectors [pdf] pdf   link   bibtex   4 downloads  
Products of Hidden Markov Models: It Takes N>1 to Tango. Taylor, G. W.; and Hinton, G. E. CoRR, abs/1205.2614. 2012.
Products of Hidden Markov Models: It Takes N>1 to Tango [link] link   Products of Hidden Markov Models: It Takes N>1 to Tango [pdf] pdf   link   bibtex   1 download  
Understanding how Deep Belief Networks perform acoustic modelling. Mohamed, A.; Hinton, G. E.; and Penn, G. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 4273-4276, 2012.
Understanding how Deep Belief Networks perform acoustic modelling [link] link   Understanding how Deep Belief Networks perform acoustic modelling [pdf] pdf   link   bibtex   3 downloads  
Deep Lambertian Networks. Tang, Y.; Salakhutdinov, R.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), 2012.
Deep Lambertian Networks [link] link   Deep Lambertian Networks [pdf] pdf   link   bibtex   1 download  
Deep Mixtures of Factor Analysers. Tang, Y.; Salakhutdinov, R.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), 2012.
Deep Mixtures of Factor Analysers [link] link   Deep Mixtures of Factor Analysers [pdf] pdf   link   bibtex   1 download  
Learning to Label Aerial Images from Noisy Data. Mnih, V.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), 2012.
Learning to Label Aerial Images from Noisy Data [link] link   Learning to Label Aerial Images from Noisy Data [pdf] pdf   link   bibtex  
Introduction to the Special Section on Deep Learning for Speech and Language Processing. Yu, D.; Hinton, G. E.; Morgan, N.; Chien, J.; and Sagayama, S. IEEE Transactions on Audio, Speech & Language Processing (TASLP), 20(1): 4-6. 2012.
Introduction to the Special Section on Deep Learning for Speech and Language Processing [link] link   link   bibtex   3 downloads  
Acoustic Modeling Using Deep Belief Networks. Mohamed, A.; Dahl, G. E.; and Hinton, G. E. IEEE Transactions on Audio, Speech & Language Processing (TASLP), 20(1): 14-22. 2012.
Acoustic Modeling Using Deep Belief Networks [link] link   Acoustic Modeling Using Deep Belief Networks [pdf] pdf   link   bibtex   2 downloads  
Visualizing non-metric similarities in multiple maps. van der Maaten, L.; and Hinton, G. E. Machine Learning (ML), 87(1): 33-55. 2012.
Visualizing non-metric similarities in multiple maps [link] link   Visualizing non-metric similarities in multiple maps [pdf] pdf   link   bibtex  
ImageNet Classification with Deep Convolutional Neural Networks. Krizhevsky, A.; Sutskever, I.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 1106-1114, 2012.
ImageNet Classification with Deep Convolutional Neural Networks [pdf] link   ImageNet Classification with Deep Convolutional Neural Networks [pdf] pdf   link   bibtex   9 downloads  
A Better Way to Pretrain Deep Boltzmann Machines. Salakhutdinov, R.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 2456-2464, 2012.
A Better Way to Pretrain Deep Boltzmann Machines [pdf] link   A Better Way to Pretrain Deep Boltzmann Machines [pdf] pdf   link   bibtex  
An Efficient Learning Procedure for Deep Boltzmann Machines. Salakhutdinov, R.; and Hinton, G. E. Neural Computation (NECO), 24(8): 1967-2006. 2012.
An Efficient Learning Procedure for Deep Boltzmann Machines [link] link   An Efficient Learning Procedure for Deep Boltzmann Machines [pdf] pdf   link   bibtex  
A Practical Guide to Training Restricted Boltzmann Machines. Hinton, G. E. In Proceedings of Neural Networks: Tricks of the Trade (2nd ed.), pages 599-619. 2012.
A Practical Guide to Training Restricted Boltzmann Machines [link] link   link   bibtex  
Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. Hinton, G. E.; Deng, L.; Yu, D.; Dahl, G. E.; Mohamed, A.; Jaitly, N.; Senior, A.; Vanhoucke, V.; Nguyen, P.; Sainath, T. N; and others Signal Processing Magazine, IEEE, 29(6): 82–97. 2012.
link   bibtex  
  2011 (13)
Modeling the joint density of two images under a variety of transformations. Susskind, J. M.; Hinton, G. E.; Memisevic, R.; and Pollefeys, M. In Proceedings of Computer Vision and Pattern Recognition (CVPR), pages 2793-2800, 2011.
Modeling the joint density of two images under a variety of transformations [link] link   Modeling the joint density of two images under a variety of transformations [pdf] pdf   link   bibtex  
On deep generative models with applications to recognition. Ranzato, M.; Susskind, J. M.; Mnih, V.; and Hinton, G. E. In Proceedings of Computer Vision and Pattern Recognition (CVPR), pages 2857-2864, 2011.
On deep generative models with applications to recognition [link] link   On deep generative models with applications to recognition [pdf] pdf   link   bibtex   1 download  
A better way to learn features: technical perspective. Hinton, G. E. Commun. ACM (CACM), 54(10): 94. 2011.
A better way to learn features: technical perspective [link] link   link   bibtex   2 downloads  
Using very deep autoencoders for content-based image retrieval. Krizhevsky, A.; and Hinton, G. E. In Proceedings of The European Symposium on Artificial Neural Networks (ESANN), 2011.
Using very deep autoencoders for content-based image retrieval [pdf] link   Using very deep autoencoders for content-based image retrieval [pdf] pdf   link   bibtex   3 downloads  
Transforming Auto-Encoders. Hinton, G. E.; Krizhevsky, A.; and Wang, S. D. In Proceedings of International Conference on Artificial Neural Networks (ICANN), pages 44-51, 2011.
Transforming Auto-Encoders [link] link   Transforming Auto-Encoders [pdf] pdf   link   bibtex   2 downloads  
Deep Belief Networks using discriminative features for phone recognition. Mohamed, A.; Sainath, T. N.; Dahl, G. E.; Ramabhadran, B.; Hinton, G. E.; and Picheny, M. A. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 5060-5063, 2011.
Deep Belief Networks using discriminative features for phone recognition [link] link   Deep Belief Networks using discriminative features for phone recognition [pdf] pdf   link   bibtex   1 download  
Deep belief nets for natural language call-routing. Sarikaya, R.; Hinton, G. E.; and Ramabhadran, B. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 5680-5683, 2011.
Deep belief nets for natural language call-routing [link] link   Deep belief nets for natural language call-routing [pdf] pdf   link   bibtex   1 download  
Learning a better representation of speech soundwaves using restricted boltzmann machines. Jaitly, N.; and Hinton, G. E. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 5884-5887, 2011.
Learning a better representation of speech soundwaves using restricted boltzmann machines [link] link   Learning a better representation of speech soundwaves using restricted boltzmann machines [pdf] pdf   link   bibtex   3 downloads  
Generating Text with Recurrent Neural Networks. Sutskever, I.; Martens, J.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), pages 1017-1024, 2011.
link   bibtex  
Two Distributed-State Models For Generating High-Dimensional Time Series. Taylor, G. W.; Hinton, G. E.; and Roweis, S. T. Journal of Machine Learning Research (JMLR), 12: 1025-1068. 2011.
Two Distributed-State Models For Generating High-Dimensional Time Series [link] link   link   bibtex  
Conditional Restricted Boltzmann Machines for Structured Output Prediction. Mnih, V.; Larochelle, H.; and Hinton, G. E. In Proceedings of Uncertainty in Artificial Intelligence (UAI), pages 514-522, 2011.
Conditional Restricted Boltzmann Machines for Structured Output Prediction [link] link   Conditional Restricted Boltzmann Machines for Structured Output Prediction [pdf] pdf   link   bibtex   1 download  
A new way to learn acoustic events. Jaitly, N.; and Hinton, G. E. Advances in Neural Information Processing Systems, 24. 2011.
A new way to learn acoustic events [pdf] pdf   link   bibtex   2 downloads  
Discovering Binary Codes for Documents by Learning Deep Generative Models. Hinton, G.; and Salakhutdinov, R. Topics in Cognitive Science, 3(1): 74–91. 2011.
Discovering Binary Codes for Documents by Learning Deep Generative Models [link] link   doi   link   bibtex   1 download  
  2010 (18)
Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images. Ranzato, M.; Krizhevsky, A.; and Hinton, G. E. In Proceedings of AISTATS, pages 621-628, 2010.
Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images [link] link   Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images [pdf] pdf   link   bibtex  
Dynamical binary latent variable models for 3D human pose tracking. Taylor, G. W.; Sigal, L.; Fleet, D. J.; and Hinton, G. E. In Proceedings of Computer Vision and Pattern Recognition (CVPR), pages 631-638, 2010.
Dynamical binary latent variable models for 3D human pose tracking [link] link   Dynamical binary latent variable models for 3D human pose tracking [pdf] pdf   link   bibtex  
Modeling pixel means and covariances using factorized third-order boltzmann machines. Ranzato, M.; and Hinton, G. E. In Proceedings of Computer Vision and Pattern Recognition (CVPR), pages 2551-2558, 2010.
Modeling pixel means and covariances using factorized third-order boltzmann machines [link] link   Modeling pixel means and covariances using factorized third-order boltzmann machines [pdf] pdf   link   bibtex   10 downloads  
Learning to Detect Roads in High-Resolution Aerial Images. Mnih, V.; and Hinton, G. E. In Proceedings of European Conference on Computer Vision (ECCV), pages 210-223, 2010.
Learning to Detect Roads in High-Resolution Aerial Images [link] link   Learning to Detect Roads in High-Resolution Aerial Images [pdf] pdf   link   bibtex   3 downloads  
Boltzmann Machines. Hinton, G. E. In Proceedings of Encyclopedia of Machine Learning, pages 132-136. 2010.
Boltzmann Machines [link] link   link   bibtex   2 downloads  
Deep Belief Nets. Hinton, G. E. In Proceedings of Encyclopedia of Machine Learning, pages 267-269. 2010.
Deep Belief Nets [link] link   link   bibtex   1 download  
Phone recognition using Restricted Boltzmann Machines. Mohamed, A.; and Hinton, G. E. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 4354-4357, 2010.
Phone recognition using Restricted Boltzmann Machines [link] link   Phone recognition using Restricted Boltzmann Machines [pdf] pdf   link   bibtex   3 downloads  
Rectified Linear Units Improve Restricted Boltzmann Machines. Nair, V.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), pages 807-814, 2010.
Rectified Linear Units Improve Restricted Boltzmann Machines [pdf] link   Rectified Linear Units Improve Restricted Boltzmann Machines [pdf] pdf   link   bibtex   3 downloads  
Binary coding of speech spectrograms using a deep auto-encoder. Deng, L.; Seltzer, M. L.; Yu, D.; Acero, A.; Mohamed, A.; and Hinton, G. E. In Proceedings of Conference of the International Speech Communication Association (INTERSPEECH), pages 1692-1695, 2010.
Binary coding of speech spectrograms using a deep auto-encoder [link] link   Binary coding of speech spectrograms using a deep auto-encoder [pdf] pdf   link   bibtex  
Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine. Dahl, G. E.; Ranzato, M.; Mohamed, A.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 469-477, 2010.
Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine [pdf] link   Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine [pdf] pdf   link   bibtex   11 downloads  
Learning to combine foveal glimpses with a third-order Boltzmann machine. Larochelle, H.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 1243-1251, 2010.
Learning to combine foveal glimpses with a third-order Boltzmann machine [pdf] link   Learning to combine foveal glimpses with a third-order Boltzmann machine [pdf] pdf   link   bibtex  
Gated Softmax Classification. Memisevic, R.; Zach, C.; Hinton, G. E.; and Pollefeys, M. In Proceedings of Neural Information Processing Systems (NIPS), pages 1603-1611, 2010.
Gated Softmax Classification [pdf] link   Gated Softmax Classification [pdf] pdf   link   bibtex   1 download  
Generating more realistic images using gated MRF's. Ranzato, M.; Mnih, V.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 2002-2010, 2010.
Generating more realistic images using gated MRF's [pdf] link   link   bibtex  
Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines. Memisevic, R.; and Hinton, G. E. Neural Computation (NECO), 22(6): 1473-1492. 2010.
Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines [link] link   Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines [pdf] pdf   link   bibtex  
Comparing Classification Methods for Longitudinal fMRI Studies. Schmah, T.; Yourganov, G.; Zemel, R. S.; Hinton, G. E.; Small, S. L.; and Strother, S. C. Neural Computation (NECO), 22(11): 2729-2762. 2010.
Comparing Classification Methods for Longitudinal fMRI Studies [link] link   link   bibtex   1 download  
Temporal-Kernel Recurrent Neural Networks. Sutskever, I.; and Hinton, G. E. Neural Networks (NN), 23(2): 239-243. 2010.
Temporal-Kernel Recurrent Neural Networks [link] link   link   bibtex  
Generating more realistic images using gated MRF's. Ranzato, M.; Mnih, V.; and Hinton, G. E. In Lafferty, J. D.; Williams, C. K. I.; Shawe-Taylor, J.; Zemel, R. S.; and Culotta, A., editor(s), NIPS, pages 2002-2010, 2010. Curran Associates, Inc.
Generating more realistic images using gated MRF's. [pdf]Link   Generating more realistic images using gated MRF's. [link] link   Generating more realistic images using gated MRF's. [pdf] pdf   link   bibtex   1 download  
Learning to represent visual input. Hinton, G. E. Philosophical Transactions of the Royal Society B: Biological Sciences, 365(1537): 177–184. January 2010.
Learning to represent visual input [link] link   Learning to represent visual input [pdf] pdf   doi   link   bibtex   abstract   1 download  
  2009 (14)
Deep Boltzmann Machines. Salakhutdinov, R.; and Hinton, G. E. In Proceedings of AISTATS, pages 448-455, 2009.
Deep Boltzmann Machines [link] link   Deep Boltzmann Machines [pdf] pdf   link   bibtex   3 downloads  
Learning Generative Texture Models with extended Fields-of-Experts. Heess, N.; Williams, C. K. I.; and Hinton, G. E. In Proceedings of British Machine Vision Conference (BMVC), pages 1-11, 2009.
Learning Generative Texture Models with extended Fields-of-Experts [link] link   Learning Generative Texture Models with extended Fields-of-Experts [pdf] pdf   link   bibtex  
Modeling pigeon behavior using a Conditional Restricted Boltzmann Machine. Zeiler, M. D.; Taylor, G. W.; Troje, N. F.; and Hinton, G. E. In Proceedings of The European Symposium on Artificial Neural Networks (ESANN), 2009.
Modeling pigeon behavior using a Conditional Restricted Boltzmann Machine [pdf] link   Modeling pigeon behavior using a Conditional Restricted Boltzmann Machine [pdf] pdf   link   bibtex  
Factored conditional restricted Boltzmann Machines for modeling motion style. Taylor, G. W.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), pages 129, 2009.
Factored conditional restricted Boltzmann Machines for modeling motion style [link] link   Factored conditional restricted Boltzmann Machines for modeling motion style [pdf] pdf   link   bibtex  
Using fast weights to improve persistent contrastive divergence. Tieleman, T.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), pages 130, 2009.
Using fast weights to improve persistent contrastive divergence [link] link   Using fast weights to improve persistent contrastive divergence [pdf] pdf   link   bibtex  
Workshop summary: Workshop on learning feature hierarchies. Yu, K.; Salakhutdinov, R.; LeCun, Y.; Hinton, G. E.; and Bengio, Y. In Proceedings of International Conference on Machine Learning (ICML), pages 165, 2009.
Workshop summary: Workshop on learning feature hierarchies [link] link   link   bibtex  
Semantic hashing. Salakhutdinov, R.; and Hinton, G. E. Int. J. Approx. Reasoning (IJAR), 50(7): 969-978. 2009.
Semantic hashing [link] link   Semantic hashing [pdf] pdf   link   bibtex   2 downloads  
3D Object Recognition with Deep Belief Nets. Nair, V.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 1339-1347, 2009.
3D Object Recognition with Deep Belief Nets [pdf] link   3D Object Recognition with Deep Belief Nets [pdf] pdf   link   bibtex   1 download  
Zero-shot Learning with Semantic Output Codes. Palatucci, M.; Pomerleau, D.; Hinton, G. E.; and Mitchell, T. M. In Proceedings of Neural Information Processing Systems (NIPS), pages 1410-1418, 2009.
Zero-shot Learning with Semantic Output Codes [pdf] link   Zero-shot Learning with Semantic Output Codes [pdf] pdf   link   bibtex  
Replicated Softmax: an Undirected Topic Model. Salakhutdinov, R.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 1607-1614, 2009.
Replicated Softmax: an Undirected Topic Model [pdf] link   Replicated Softmax: an Undirected Topic Model [pdf] pdf   link   bibtex  
Improving a statistical language model through non-linear prediction. Mnih, A.; Yuecheng, Z.; and Hinton, G. E. Neurocomputing (IJON), 72(7-9): 1414-1418. 2009.
Improving a statistical language model through non-linear prediction [link] link   link   bibtex   2 downloads  
Deep belief networks. Hinton, G. E. Scholarpedia, 4(5): 5947. 2009.
Deep belief networks [link] link   link   bibtex  
Products of Hidden Markov Models: It Takes N>1 to Tango. Taylor, G. W.; and Hinton, G. E. In Proceedings of Uncertainty in Artificial Intelligence (UAI), pages 522-529, 2009.
Products of Hidden Markov Models: It Takes N>1 to Tango [link] link   link   bibtex  
Deep Belief Networks for phone recognition. Mohamed, A.; Dahl, G.; and Hinton, G. NIPS 22 workshop on deep learning for speech recognition. 2009.
Deep Belief Networks for phone recognition [pdf] pdf   link   bibtex   4 downloads  
  2008 (10)
Improving a statistical language model by modulating the effects of context words. Yuecheng, Z.; Mnih, A.; and Hinton, G. E. In Proceedings of The European Symposium on Artificial Neural Networks (ESANN), pages 493-498, 2008.
Improving a statistical language model by modulating the effects of context words [pdf] link   Improving a statistical language model by modulating the effects of context words [pdf] pdf   link   bibtex  
Analysis-by-Synthesis by Learning to Invert Generative Black Boxes. Nair, V.; Susskind, J. M.; and Hinton, G. E. In Proceedings of International Conference on Artificial Neural Networks (ICANN), pages 971-981, 2008.
Analysis-by-Synthesis by Learning to Invert Generative Black Boxes [link] link   Analysis-by-Synthesis by Learning to Invert Generative Black Boxes [pdf] pdf   link   bibtex   1 download  
A Scalable Hierarchical Distributed Language Model. Mnih, A.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 1081-1088, 2008.
A Scalable Hierarchical Distributed Language Model [pdf] link   A Scalable Hierarchical Distributed Language Model [pdf] pdf   link   bibtex  
Implicit Mixtures of Restricted Boltzmann Machines. Nair, V.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 1145-1152, 2008.
Implicit Mixtures of Restricted Boltzmann Machines [pdf] link   Implicit Mixtures of Restricted Boltzmann Machines [pdf] pdf   link   bibtex  
Generative versus discriminative training of RBMs for classification of fMRI images. Schmah, T.; Hinton, G. E.; Zemel, R. S.; Small, S. L.; and Strother, S. C. In Proceedings of Neural Information Processing Systems (NIPS), pages 1409-1416, 2008.
Generative versus discriminative training of RBMs for classification of fMRI images [pdf] link   Generative versus discriminative training of RBMs for classification of fMRI images [pdf] pdf   link   bibtex  
Using matrices to model symbolic relationship. Sutskever, I.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 1593-1600, 2008.
Using matrices to model symbolic relationship [pdf] link   Using matrices to model symbolic relationship [pdf] pdf   link   bibtex   1 download  
The Recurrent Temporal Restricted Boltzmann Machine. Sutskever, I.; Hinton, G. E.; and Taylor, G. W. In Proceedings of Neural Information Processing Systems (NIPS), pages 1601-1608, 2008.
The Recurrent Temporal Restricted Boltzmann Machine [pdf] link   The Recurrent Temporal Restricted Boltzmann Machine [pdf] pdf   link   bibtex  
Deep, Narrow Sigmoid Belief Networks Are Universal Approximators. Sutskever, I.; and Hinton, G. E. Neural Computation (NECO), 20(11): 2629-2636. 2008.
Deep, Narrow Sigmoid Belief Networks Are Universal Approximators [link] link   Deep, Narrow Sigmoid Belief Networks Are Universal Approximators [pdf] pdf   link   bibtex   1 download  
Visualizing Data using t-SNE. Van der Maaten, L.; and Hinton, G. Journal of Machine Learning Research, 9(11). 2008.
Visualizing Data using t-SNE. [pdf] pdf   Visualizing Data using t-SNE. [pdf] supplementary material 25mb   link   bibtex  
Generating facial expressions with deep belief nets. Susskind, J. M.; Hinton, G. E.; Movellan, J. R.; and Anderson, A. K. Affective Computing, Emotion Modelling, Synthesis and Recognition,421–440. 2008.
Generating facial expressions with deep belief nets [pdf] pdf   link   bibtex   1 download  
  2007 (11)
Visualizing Similarity Data with a Mixture of Maps. Cook, J.; Sutskever, I.; Mnih, A.; and Hinton, G. E. In Proceedings of AISTATS, pages 67-74, 2007.
Visualizing Similarity Data with a Mixture of Maps [link] link   Visualizing Similarity Data with a Mixture of Maps [pdf] pdf   link   bibtex  
Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure. Salakhutdinov, R.; and Hinton, G. E. In Proceedings of AISTATS, pages 412-419, 2007.
Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure [link] link   Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure [pdf] pdf   link   bibtex  
Learning Multilevel Distributed Representations for High-Dimensional Sequences. Sutskever, I.; and Hinton, G. E. In Proceedings of AISTATS, pages 548-555, 2007.
Learning Multilevel Distributed Representations for High-Dimensional Sequences [link] link   Learning Multilevel Distributed Representations for High-Dimensional Sequences [pdf] pdf   link   bibtex  
Unsupervised Learning of Image Transformations. Memisevic, R.; and Hinton, G. E. In Proceedings of Computer Vision and Pattern Recognition (CVPR), 2007.
Unsupervised Learning of Image Transformations [link] link   Unsupervised Learning of Image Transformations [pdf] pdf   link   bibtex  
Three new graphical models for statistical language modelling. Mnih, A.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), pages 641-648, 2007.
Three new graphical models for statistical language modelling [link] link   Three new graphical models for statistical language modelling [pdf] pdf   link   bibtex  
Restricted Boltzmann machines for collaborative filtering. Salakhutdinov, R.; Mnih, A.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), pages 791-798, 2007.
Restricted Boltzmann machines for collaborative filtering [link] link   Restricted Boltzmann machines for collaborative filtering [pdf] pdf   link   bibtex   2 downloads  
Modeling image patches with a directed hierarchy of Markov random fields. Osindero, S.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), 2007.
Modeling image patches with a directed hierarchy of Markov random fields [pdf] link   Modeling image patches with a directed hierarchy of Markov random fields [pdf] pdf   link   bibtex  
Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes. Salakhutdinov, R.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), 2007.
Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes [pdf] link   Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes [pdf] pdf   link   bibtex  
Boltzmann machine. Hinton, G. E. Scholarpedia, 2(5): 1668. 2007.
Boltzmann machine [link] link   link   bibtex  
Learning multiple layers of representation. Hinton, G. E. Trends in Cognitive Sciences, 11(10). 2007.
Learning multiple layers of representation [pdf] pdf   link   bibtex   abstract   1 download  
To Recognize Shapes First Learn to Generate Images. Hinton, G. E. In Computational Neuroscience: Theoretical Insights into Brain Function, 2007. Elsevier
To Recognize Shapes First Learn to Generate Images [pdf] draft   link   bibtex   abstract  
  2006 (5)
Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation. Hinton, G. E.; Osindero, S.; Welling, M.; and Teh, Y. W. Cognitive Science (COGSCI), 30(4): 725-731. 2006.
Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation [link] link   Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation [ps] ps   Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation [pdf] pdf   link   bibtex  
Modeling Human Motion Using Binary Latent Variables. Taylor, G. W.; Hinton, G. E.; and Roweis, S. T. In Proceedings of Neural Information Processing Systems (NIPS), pages 1345-1352, 2006.
Modeling Human Motion Using Binary Latent Variables [pdf] link   Modeling Human Motion Using Binary Latent Variables [pdf] pdf   link   bibtex   1 download  
Topographic Product Models Applied to Natural Scene Statistics. Osindero, S.; Welling, M.; and Hinton, G. E. Neural Computation (NECO), 18(2): 381-414. 2006.
Topographic Product Models Applied to Natural Scene Statistics [link] link   Topographic Product Models Applied to Natural Scene Statistics [pdf] pdf   link   bibtex  
A Fast Learning Algorithm for Deep Belief Nets. Hinton, G. E.; Osindero, S.; and Teh, Y. W. Neural Computation (NECO), 18(7): 1527-1554. 2006.
A Fast Learning Algorithm for Deep Belief Nets [link] link   A Fast Learning Algorithm for Deep Belief Nets [pdf] pdf   link   bibtex   4 downloads  
Reducing the dimensionality of data with neural networks. Hinton, G. E.; and Salakhutdinov, R. R. Science, 313(5786): 504-507. July 2006.
Reducing the dimensionality of data with neural networks [link] link   Reducing the dimensionality of data with neural networks [link] abstract   Reducing the dimensionality of data with neural networks [pdf] paper   Reducing the dimensionality of data with neural networks [pdf] supporting online material   Reducing the dimensionality of data with neural networks [link] matlab code   doi   link   bibtex   abstract   14 downloads  
  2005 (6)
What kind of graphical model is the brain?. Hinton, G. E. In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), pages 1765-, 2005.
What kind of graphical model is the brain? [pdf] link   What kind of graphical model is the brain? [link] psgz   What kind of graphical model is the brain? [pdf] pdf   link   bibtex   2 downloads  
Inferring Motor Programs from Images of Handwritten Digits. Hinton, G. E.; and Nair, V. In Proceedings of Neural Information Processing Systems (NIPS), 2005.
Inferring Motor Programs from Images of Handwritten Digits [pdf] link   Inferring Motor Programs from Images of Handwritten Digits [link] psgz   Inferring Motor Programs from Images of Handwritten Digits [pdf] pdf   link   bibtex   1 download  
Improving dimensionality reduction with spectral gradient descent. Memisevic, R.; and Hinton, G. E. Neural Networks (NN), 18(5-6): 702-710. 2005.
Improving dimensionality reduction with spectral gradient descent [link] link   link   bibtex  
Learning causally linked markov random fields. Hinton, G. E.; Osindero, S.; and Bao, K. In Proceedings of the 10th International Workshop on Artificial Intelligence and Statistics, pages 128–135, 2005.
Learning causally linked markov random fields [link] psgz   Learning causally linked markov random fields [pdf] pdf   link   bibtex   4 downloads  
Learning Unreliable Constraints using Contrastive Divergence. Mnih, A.; and E., H. G. In Proceedings of the International Joint Conference on Neural Networks, Montreal, 2005.
Learning Unreliable Constraints using Contrastive Divergence [link] psgz   Learning Unreliable Constraints using Contrastive Divergence [pdf] pdf   link   bibtex  
On contrastive divergence learning. Carreira-Perpinan, M. A.; and Hinton, G. E. In Proceedings of the tenth international workshop on artificial intelligence and statistics, pages 33–40, 2005. Society for Artificial Intelligence and Statistics NP
On contrastive divergence learning [pdf] pdf   link   bibtex   2 downloads  
  2004 (6)
Probabilistic sequential independent components analysis. Welling, M.; Zemel, R. S.; and Hinton, G. E. IEEE Transactions on Neural Networks (TNN), 15(4): 838-849. 2004.
Probabilistic sequential independent components analysis [link] link   Probabilistic sequential independent components analysis [link] psgz   Probabilistic sequential independent components analysis [pdf] pdf   link   bibtex   1 download  
Reinforcement Learning with Factored States and Actions. Sallans, B.; and Hinton, G. E. Journal of Machine Learning Research (JMLR), 5: 1063-1088. 2004.
Reinforcement Learning with Factored States and Actions [pdf]Paper   link   bibtex   1 download  
Exponential Family Harmoniums with an Application to Information Retrieval. Welling, M.; Rosen-Zvi, M.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), 2004.
Exponential Family Harmoniums with an Application to Information Retrieval [pdf] link   Exponential Family Harmoniums with an Application to Information Retrieval [link] psgz   Exponential Family Harmoniums with an Application to Information Retrieval [pdf] pdf   link   bibtex   2 downloads  
Multiple Relational Embedding. Memisevic, R.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), 2004.
Multiple Relational Embedding [pdf] link   Multiple Relational Embedding [link] psgz   Multiple Relational Embedding [pdf] pdf   link   bibtex  
Neighbourhood Components Analysis. Goldberger, J.; Roweis, S. T.; Hinton, G. E.; and Salakhutdinov, R. In Proceedings of Neural Information Processing Systems (NIPS), 2004.
Neighbourhood Components Analysis [pdf] link   Neighbourhood Components Analysis [pdf] pdf   link   bibtex   1 download  
Distinguishing text from graphics in on-line handwritten ink. Bishop, C. M.; Svensén, M.; and Hinton, G. E. In IWFHR, pages 142-147, 2004. IEEE Computer Society
Distinguishing text from graphics in on-line handwritten ink. [link]Link   Distinguishing text from graphics in on-line handwritten ink. [link] link   Distinguishing text from graphics in on-line handwritten ink. [pdf] pdf   link   bibtex  
  2003 (4)
Energy-Based Models for Sparse Overcomplete Representations. Teh, Y. W.; Welling, M.; Osindero, S.; and Hinton, G. E. Journal of Machine Learning Research (JMLR), 4: 1235-1260. 2003.
Energy-Based Models for Sparse Overcomplete Representations [link] link   Energy-Based Models for Sparse Overcomplete Representations [link] psgz   Energy-Based Models for Sparse Overcomplete Representations [pdf] pdf   link   bibtex   1 download  
Wormholes Improve Contrastive Divergence. Hinton, G. E.; Welling, M.; and Mnih, A. In Proceedings of Neural Information Processing Systems (NIPS), 2003.
Wormholes Improve Contrastive Divergence [pdf] link   Wormholes Improve Contrastive Divergence [link] psgz   Wormholes Improve Contrastive Divergence [pdf] pdf   link   bibtex  
Efficient Parametric Projection Pursuit Density Estimation. Welling, M.; Zemel, R. S.; and Hinton, G. E. In Proceedings of Uncertainty in Artificial Intelligence (UAI), pages 575-582, 2003.
Efficient Parametric Projection Pursuit Density Estimation [link] link   Efficient Parametric Projection Pursuit Density Estimation [link] psgz   link   bibtex  
The Ups and Downs of Hebb Synapses. Hinton, G. E. Canadian Psychology/Psychologie canadienne, 44(1): 10-13. 2003.
The Ups and Downs of Hebb Synapses [pdf] pdf   link   bibtex  
  2002 (11)
Recognizing handwritten digits using hierarchical products of experts. Mayraz, G.; and Hinton, G. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 24(2): 189-197. Feb 2002.
doi   link   bibtex   abstract  
In Memory of Ray Reiter (1939-2002). Pirri, F.; Hinton, G. E.; and Levesque, H. J. AI Magazine (AIM), 23(4): 93. 2002.
In Memory of Ray Reiter (1939-2002) [link] link   link   bibtex  
Local Physical Models for Interactive Character Animation. Oore, S.; Terzopoulos, D.; and Hinton, G. E. Comput. Graph. Forum (CGF), 21(3): 337-346. 2002.
Local Physical Models for Interactive Character Animation [link] link   Local Physical Models for Interactive Character Animation [pdf] pdf   link   bibtex  
A Desktop Input Device and Interface for Interactive 3D Character Animation. Oore, S.; Terzopoulos, D.; and Hinton, G. E. In Proceedings of Graphics Interface, pages 133-140, 2002.
A Desktop Input Device and Interface for Interactive 3D Character Animation [link] link   A Desktop Input Device and Interface for Interactive 3D Character Animation [pdf] pdf   link   bibtex  
A New Learning Algorithm for Mean Field Boltzmann Machines. Welling, M.; and Hinton, G. E. In Proceedings of International Conference on Artificial Neural Networks (ICANN), pages 351-357, 2002.
A New Learning Algorithm for Mean Field Boltzmann Machines [link] link   A New Learning Algorithm for Mean Field Boltzmann Machines [pdf] pdf   link   bibtex   1 download  
Recognizing Handwritten Digits Using Hierarchical Products of Experts. Mayraz, G.; and Hinton, G. E. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI), 24(2): 189-197. 2002.
Recognizing Handwritten Digits Using Hierarchical Products of Experts [link] link   Recognizing Handwritten Digits Using Hierarchical Products of Experts [pdf] pdf   link   bibtex  
Self Supervised Boosting. Welling, M.; Zemel, R. S.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 665-672, 2002.
Self Supervised Boosting [pdf] link   Self Supervised Boosting [pdf] pdf   Self Supervised Boosting [link] psgz   link   bibtex  
Stochastic Neighbor Embedding. Hinton, G. E.; and Roweis, S. T. In Proceedings of Neural Information Processing Systems (NIPS), pages 833-840, 2002.
Stochastic Neighbor Embedding [pdf] link   Stochastic Neighbor Embedding [link] psgz   Stochastic Neighbor Embedding [pdf] pdf   link   bibtex  
Learning Sparse Topographic Representations with Products of Student-t Distributions. Welling, M.; Hinton, G. E.; and Osindero, S. In Proceedings of Neural Information Processing Systems (NIPS), pages 1359-1366, 2002.
Learning Sparse Topographic Representations with Products of Student-t Distributions [pdf] link   Learning Sparse Topographic Representations with Products of Student-t Distributions [link] psgz   Learning Sparse Topographic Representations with Products of Student-t Distributions [pdf] pdf   link   bibtex  
Training Products of Experts by Minimizing Contrastive Divergence. Hinton, G. E. Neural Computation (NECO), 14(8): 1771-1800. 2002.
Training Products of Experts by Minimizing Contrastive Divergence [link] link   Training Products of Experts by Minimizing Contrastive Divergence [pdf] pdf   link   bibtex   2 downloads  
Classical and Bayesian inference in neuroimaging: theory. Friston, K. J.; Penny, W.; Phillips, C.; Kiebel, S.; Hinton, G.; and Ashburner, J. NeuroImage, 16(2): 465–483. 2002.
Classical and Bayesian inference in neuroimaging: theory [pdf] pdf   link   bibtex  
  2001 (9)
Learning Distributed Representations of Concepts Using Linear Relational Embedding. Paccanaro, A.; and Hinton, G. E. IEEE Trans. Knowl. Data Eng. (TKDE), 13(2): 232-244. 2001.
Learning Distributed Representations of Concepts Using Linear Relational Embedding [link] link   Learning Distributed Representations of Concepts Using Linear Relational Embedding [link] abstract   Learning Distributed Representations of Concepts Using Linear Relational Embedding [link] psgz   Learning Distributed Representations of Concepts Using Linear Relational Embedding [pdf] pdf   link   bibtex   1 download  
Learning Hierarchical Structures with Linear Relational Embedding. Paccanaro, A.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 857-864, 2001.
Learning Hierarchical Structures with Linear Relational Embedding [link] link   Learning Hierarchical Structures with Linear Relational Embedding [pdf] pdf   Learning Hierarchical Structures with Linear Relational Embedding [ps] ps   Learning Hierarchical Structures with Linear Relational Embedding [link] psgz   link   bibtex   1 download  
Global Coordination of Local Linear Models. Roweis, S. T.; Saul, L. K.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 889-896, 2001.
Global Coordination of Local Linear Models [link] link   Global Coordination of Local Linear Models [link] psgz   Global Coordination of Local Linear Models [pdf] pdf   link   bibtex  
Relative Density Nets: A New Way to Combine Backpropagation with HMM's. Brown, A. D.; and Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 1149-1156, 2001.
Relative Density Nets: A New Way to Combine Backpropagation with HMM's [link] link   link   bibtex  
Discovering Multiple Constraints that are Frequently Approximately Satisfied. Hinton, G. E.; and Teh, Y. W. In Proceedings of Uncertainty in Artificial Intelligence (UAI), pages 227-234, 2001.
Discovering Multiple Constraints that are Frequently Approximately Satisfied [link] link   Discovering Multiple Constraints that are Frequently Approximately Satisfied [link] psgz   Discovering Multiple Constraints that are Frequently Approximately Satisfied [pdf] pdf   link   bibtex  
Relative Density Nets: A New Way to Combine Backpropagation with HMM's. Brown, A. D.; and Hinton, G. E. In Dietterich, T. G.; Becker, S.; and Ghahramani, Z., editor(s), NIPS, pages 1149-1156, 2001. MIT Press
Relative Density Nets: A New Way to Combine Backpropagation with HMM's. [link]Link   Relative Density Nets: A New Way to Combine Backpropagation with HMM's. [link] link   Relative Density Nets: A New Way to Combine Backpropagation with HMM's. [pdf] pdf   Relative Density Nets: A New Way to Combine Backpropagation with HMM's. [ps] ps   Relative Density Nets: A New Way to Combine Backpropagation with HMM's. [link] psgz   link   bibtex  
A new view of ICA. Hinton, G. E.; Welling, M.; Teh, Y. W.; and Osindero, S. In Int. Conf. on Independent Component Analysis and Blind Source Separation, 2001.
A new view of ICA [link] psgz   A new view of ICA [pdf] pdf   link   bibtex  
Training many small hidden markov models. Hinton, G.; and Brown, A. . 2001.
Training many small hidden markov models [ps] ps   Training many small hidden markov models [ps] psgz   Training many small hidden markov models [pdf] pdf   link   bibtex  
Products of hidden markov models. Brown, A. D.; and Hinton, G. E. In In Proceedings of Artificial Intelligence and Statistics, 2001.
Products of hidden markov models [link] abstract   Products of hidden markov models [ps] ps   Products of hidden markov models [ps] psgz   Products of hidden markov models [pdf] pdf   link   bibtex  
  2000 (9)
Modeling High-Dimensional Data by Combining Simple Experts. Hinton, G. E. In Proceedings of AAAI/IAAI, pages 1159-1164, 2000.
Modeling High-Dimensional Data by Combining Simple Experts [link] link   Modeling High-Dimensional Data by Combining Simple Experts [pdf] pdf   link   bibtex  
Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space. Paccanaro, A.; and Hinton, G. E. In Proceedings of International Conference on Machine Learning (ICML), pages 711-718, 2000.
Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space [ps] ps   Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space [link] psgz   Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space [pdf] pdf   link   bibtex   1 download  
Extracting Distributed Representations of Concepts and Relations from Positive and Negative Propositions. Paccanaro, A.; and Hinton, G. E. In Proceedings of International Joint Conference on Neural Network (IJCNN), pages 259-264, 2000.
Extracting Distributed Representations of Concepts and Relations from Positive and Negative Propositions [link] link   Extracting Distributed Representations of Concepts and Relations from Positive and Negative Propositions [pdf] pdf   Extracting Distributed Representations of Concepts and Relations from Positive and Negative Propositions [ps] ps   Extracting Distributed Representations of Concepts and Relations from Positive and Negative Propositions [link] psgz   link   bibtex