作者
Yoshua Bengio
Machine Learning
Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews
NICE: Non-linear Independent Components Estimation
Comments 11 pages and 2 pages Appendix, workshop paper at ICLR 2015
Embedding Word Similarity with Neural Machine Translation
Comments arXiv admin note: text overlap with arXiv:1410.0718
EmoNets: Multimodal deep learning approaches for emotion recognition in video
FitNets: Hints for Thin Deep Nets
GSNs : Generative Stochastic Networks
Comments arXiv admin note: substantial text overlap with arXiv:1306.1091
The Statistical Inefficiency of Sparse Coding for Images (or, One Gabor to Rule them All)
Comments 9 pages, 8 figures
On Using Very Large Target Vocabulary for Neural Machine Translation
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Comments Presented in NIPS 2014 Deep Learning and Representation Learning Workshop
How transferable are features in deep neural networks?
Comments To appear in Advances in Neural Information Processing Systems 27 (NIPS 2014)
Journal ref Advances in Neural Information Processing Systems 27, pages 3320-3328. Dec. 2014
Iterative Neural Autoregressive Distribution Estimator (NADE-k)
Comments Accepted at Neural Information Processing Systems (NIPS) 2014
End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
Comments As accepted to: Deep Learning and Representation Learning Workshop, NIPS 2014
Not All Neural Embeddings are Born Equal
Comments 4 pages plus 1 page of references
On the Challenges of Physical Implementations of RBMs
Journal ref Proc. AAAI 2014, pp. 1199-1205
On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
Comments Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8)
Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation
Comments Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8)
Deep Directed Generative Autoencoders
Deep Tempering
How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
Comments EMNLP 2014
Multimodal Transitions for Generative Stochastic Networks
Comments 7 figures, 9 pages, submitted to ICLR14
On the Equivalence Between Deep NADE and Generative Stochastic Networks
Comments ECML/PKDD 2014
Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks
Comments ECML/PKDD 2014
What Regularized Auto-Encoders Learn from the Data Generating Distribution
Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning
Generative Adversarial Networks
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
Comments The theoretical review and analysis in this article draw heavily from arXiv:1405.4604 [cs.LG]
