ICLR 2017

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

iclr2015:accepted-main [2017/10/08 15:18]
rnogueira
iclr2015:accepted-main [2017/10/08 15:40] (current)
rnogueira
Line 1: Line 1:
-==== Conference Oral Presentations ==== +==== Main Conference ​Oral Presentations ==== 
-  ​[[http://​arxiv.org/​abs/​1412.6623|Word Representations via Gaussian Embedding]],​ Luke Vilnis and Andrew McCallum +  ​[[http://​arxiv.org/​abs/​1412.6623|Word Representations via Gaussian Embedding]],​ Luke Vilnis and Andrew McCallum 
-  ​[[http://​arxiv.org/​abs/​1412.6632|Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)]], Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, and Alan Yuille +  ​[[http://​arxiv.org/​abs/​1412.6632|Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)]], Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, and Alan Yuille 
-  ​[[http://​arxiv.org/​abs/​1412.5903|Deep Structured Output Learning for Unconstrained Text Recognition]],​ Max Jaderberg, Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman +  ​[[http://​arxiv.org/​abs/​1412.5903|Deep Structured Output Learning for Unconstrained Text Recognition]],​ Max Jaderberg, Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman 
-  ​[[http://​arxiv.org/​abs/​1409.1556|Very Deep Convolutional Networks for Large-Scale Image Recognition]],​ Karen Simonyan and Andrew Zisserman +  ​[[http://​arxiv.org/​abs/​1409.1556|Very Deep Convolutional Networks for Large-Scale Image Recognition]],​ Karen Simonyan and Andrew Zisserman 
-  ​[[http://​arxiv.org/​abs/​1412.7580|Fast Convolutional Nets With fbfft: A GPU Performance Evaluation]],​ Nicolas Vasilache, Jeff Johnson, Michael Mathieu, Soumith Chintala, Serkan Piantino, and Yann LeCun +  ​[[http://​arxiv.org/​abs/​1412.7580|Fast Convolutional Nets With fbfft: A GPU Performance Evaluation]],​ Nicolas Vasilache, Jeff Johnson, Michael Mathieu, Soumith Chintala, Serkan Piantino, and Yann LeCun 
-  ​[[http://​arxiv.org/​abs/​1406.2751|Reweighted Wake-Sleep]],​ Jorg Bornschein and Yoshua Bengio +  ​[[http://​arxiv.org/​abs/​1406.2751|Reweighted Wake-Sleep]],​ Jorg Bornschein and Yoshua Bengio 
-  ​[[http://​arxiv.org/​abs/​1412.6626|The local low-dimensionality of natural images]], Olivier Henaff, Johannes Balle, Neil Rabinowitz, and Eero Simoncelli +  ​[[http://​arxiv.org/​abs/​1412.6626|The local low-dimensionality of natural images]], Olivier Henaff, Johannes Balle, Neil Rabinowitz, and Eero Simoncelli 
-  ​[[http://​arxiv.org/​abs/​1410.3916|Memory Networks]], Jason Weston, Sumit Chopra, and Antoine Bordes +  ​[[http://​arxiv.org/​abs/​1410.3916|Memory Networks]], Jason Weston, Sumit Chopra, and Antoine Bordes 
-  ​[[http://​arxiv.org/​abs/​1412.6856|Object detectors emerge in Deep Scene CNNs]], Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba +  ​[[http://​arxiv.org/​abs/​1412.6856|Object detectors emerge in Deep Scene CNNs]], Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba 
-  ​[[http://​arxiv.org/​abs/​1412.6544|Qualitatively characterizing neural network optimization problems]], Ian Goodfellow and Oriol Vinyals +  ​[[http://​arxiv.org/​abs/​1412.6544|Qualitatively characterizing neural network optimization problems]], Ian Goodfellow and Oriol Vinyals 
-  ​[[http://​arxiv.org/​abs/​1409.0473|Neural Machine Translation by Jointly Learning to Align and Translate]],​ Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio+  ​[[http://​arxiv.org/​abs/​1409.0473|Neural Machine Translation by Jointly Learning to Align and Translate]],​ Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio
  
-==== May 9 Conference Poster Session ==== 
-^ **Board** ^ **Presentation** | 
-| 2 | [[http://​arxiv.org/​abs/​1412.6550|FitNets:​ Hints for Thin Deep Nets]], Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio | 
-| 3 | [[http://​arxiv.org/​abs/​1406.2989|Techniques for Learning Binary Stochastic Feedforward Neural Networks]], Tapani Raiko, Mathias Berglund, Guillaume Alain, and Laurent Dinh | 
-| 4 | [[http://​arxiv.org/​abs/​1406.2751|Reweighted Wake-Sleep]],​ Jorg Bornschein and Yoshua Bengio | 
-| 5 | [[http://​arxiv.org/​abs/​1412.7062|Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs]], Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan Yuille | 
-| 7 | [[http://​arxiv.org/​abs/​1412.7755|Multiple Object Recognition with Visual Attention]],​ Jimmy Ba, Volodymyr Mnih, and Koray Kavukcuoglu | 
-| 8 | [[http://​arxiv.org/​abs/​1411.3784|Deep Narrow Boltzmann Machines are Universal Approximators]],​ Guido Montufar | 
-| 9 | [[http://​arxiv.org/​abs/​1412.7659|Transformation Properties of Learned Visual Representations]],​ Taco Cohen and Max Welling | 
-| 10 | [[http://​arxiv.org/​abs/​1412.7028|Joint RNN-Based Greedy Parsing and Word Composition]],​ Joël Legrand and Ronan Collobert | 
-| 11 | [[http://​arxiv.org/​abs/​1412.6980|Adam:​ A Method for Stochastic Optimization]],​ Jimmy Ba and Diederik Kingma | 
-| 13 | [[http://​arxiv.org/​abs/​1409.0473|Neural Machine Translation by Jointly Learning to Align and Translate]],​ Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio | 
-| 15 | [[http://​arxiv.org/​abs/​1406.3269|Scheduled denoising autoencoders]],​ Krzysztof Geras and Charles Sutton | 
-| 16 | [[http://​arxiv.org/​abs/​1412.6575|Embedding Entities and Relations for Learning and Inference in Knowledge Bases]], Bishan Yang, Scott Yih, Xiaodong He, Jianfeng Gao, and Li Deng | 
-| 18 | [[http://​arxiv.org/​abs/​1412.6626|The local low-dimensionality of natural images]], Olivier Henaff, Johannes Balle, Neil Rabinowitz, and Eero Simoncelli | 
-| 20 | [[http://​arxiv.org/​abs/​1412.6572|Explaining and Harnessing Adversarial Examples]], Ian Goodfellow, Jon Shlens, and Christian Szegedy | 
-| 22 | [[http://​arxiv.org/​abs/​1412.6577|Modeling Compositionality with Multiplicative Recurrent Neural Networks]], Ozan Irsoy and Claire Cardie | 
-| 24 | [[http://​arxiv.org/​abs/​1409.1556|Very Deep Convolutional Networks for Large-Scale Image Recognition]],​ Karen Simonyan and Andrew Zisserman | 
-| 25 | [[http://​arxiv.org/​abs/​1412.6553|Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition]],​ Vadim Lebedev, Yaroslav Ganin, Victor Lempitsky, Maksim Rakhuba, and Ivan Oseledets | 
-| 27 | [[http://​arxiv.org/​abs/​1412.6632|Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)]], Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, and Alan Yuille | 
-| 28 | [[http://​arxiv.org/​abs/​1412.5903|Deep Structured Output Learning for Unconstrained Text Recognition]],​ Max Jaderberg, Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman | 
-| 30 | [[http://​arxiv.org/​abs/​1402.3337|Zero-bias autoencoders and the benefits of co-adapting features]], Kishore Konda, Roland Memisevic, and David Krueger | 
-| 31 | [[http://​arxiv.org/​abs/​1412.6598|Automatic Discovery and Optimization of Parts for Image Classification]],​ Sobhan Naderi Parizi, Andrea Vedaldi, Andrew Zisserman, and Pedro Felzenszwalb | 
-| 33 | [[http://​arxiv.org/​abs/​1410.1165|Understanding Locally Competitive Networks]], Rupesh Srivastava, Jonathan Masci, Faustino Gomez, and Juergen Schmidhuber | 
-| 35 | [[http://​arxiv.org/​abs/​1412.6334|Leveraging Monolingual Data for Crosslingual Compositional Word Representations]],​ Hubert Soyer, Pontus Stenetorp, and Akiko Aizawa | 
-| 36 | [[http://​arxiv.org/​abs/​1412.6564|Move Evaluation in Go Using Deep Convolutional Neural Networks]], Chris Maddison, Aja Huang, Ilya Sutskever, and David Silver | 
-| 38 | [[http://​arxiv.org/​abs/​1412.7580|Fast Convolutional Nets With fbfft: A GPU Performance Evaluation]],​ Nicolas Vasilache, Jeff Johnson, Michael Mathieu, Soumith Chintala, Serkan Piantino, and Yann LeCun | 
-| 40 | [[http://​arxiv.org/​abs/​1412.6623|Word Representations via Gaussian Embedding]],​ Luke Vilnis and Andrew McCallum | 
-| 41 | [[http://​arxiv.org/​abs/​1412.6544|Qualitatively characterizing neural network optimization problems]], Ian Goodfellow and Oriol Vinyals | 
-| 42 | [[http://​arxiv.org/​abs/​1410.3916|Memory Networks]], Jason Weston, Sumit Chopra, and Antoine Bordes | 
-| 43 | [[http://​arxiv.org/​abs/​1412.6296|Generative Modeling of Convolutional Neural Networks]], Jifeng Dai, Yang Lu, and Ying-Nian Wu | 
-| 44 | [[http://​arxiv.org/​abs/​1412.7489|A Unified Perspective on Multi-Domain and Multi-Task Learning]], Yongxin Yang and Timothy Hospedales | 
-| 45 | [[http://​arxiv.org/​abs/​1412.6856|Object detectors emerge in Deep Scene CNNs]], Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba | 
  
-==== May 7 Workshop ​Poster ​Session ​==== +====Main Conference - Poster ​Presentations====
-^ **Board** ^ **Presentation** | +
-| 2 | [[http://​arxiv.org/​abs/​1412.7272 ​ | Learning Non-deterministic Representations with Energy-based Ensembles]],​ Maruan Al-Shedivat,​ Emre Neftci, and Gert Cauwenberghs ​                                              | +
-| 3 | [[http://​arxiv.org/​abs/​1412.7063 ​ | Diverse Embedding Neural Network Language Models]], Kartik Audhkhasi, Abhinav Sethy, and Bhuvana Ramabhadran ​                                                                  | +
-| 4 | [[http://​arxiv.org/​abs/​1412.6599 ​ | Hot Swapping for Online Adaptation of Optimization Hyperparameters]],​ Kevin Bache, Dennis Decoste, and Padhraic Smyth                                                          | +
-| 5 | [[http://​arxiv.org/​abs/​1412.7156 ​ | Representation Learning for cold-start recommendation]],​ Gabriella Contardo, Ludovic Denoyer, and Thierry Artieres ​                                                            | +
-| 6 | [[http://​arxiv.org/​abs/​1406.2080 ​ | Training Convolutional Networks with Noisy Labels]], Sainbayar Sukhbaatar, Joan Bruna, Manohar Paluri, Lubomir Bourdev, and Rob Fergus ​                                        | +
-| 7 | [[http://​arxiv.org/​abs/​1412.6806 ​ | Striving for Simplicity: ​ The All Convolutional Net]], Alexey Dosovitskiy,​ Jost Tobias Springenberg,​ Thomas Brox, and Martin Riedmiller ​                                       | +
-| 8 | [[http://​arxiv.org/​abs/​1412.7110 ​ | Learning linearly separable features for speech recognition using convolutional neural networks]], Dimitri Palaz, Mathew Magimai Doss, and Ronan Collobert ​                    | +
-| 9 | [[http://​arxiv.org/​abs/​1412.6596 ​ | Training Deep Neural Networks on Noisy Labels with Bootstrapping]],​ Scott Reed, Honglak Lee, Dragomir Anguelov, Christian Szegedy, Dumitru Erhan, and Andrew Rabinovich ​       | +
-| 10 | [[http://​arxiv.org/​abs/​1412.5896 ​ | On the Stability of Deep Networks]], Raja Giryes, Guillermo Sapiro, and Alex Bronstein ​                                                                                        | +
-| 11 | [[http://​arxiv.org/​abs/​1412.7022 ​ | Audio source separation with Discriminative Scattering Networks ]], Joan Bruna, Yann LeCun, and Pablo Sprechmann ​                                                              | +
-| 13 | [[http://​arxiv.org/​abs/​1412.8419 ​ | Simple Image Description Generator via a Linear Phrase-Based Model]], Pedro Pinheiro, Rémi Lebret, and Ronan Collobert ​                                                        | +
-| 15 | [[http://​arxiv.org/​abs/​1412.5744 ​ | Stochastic Descent Analysis of Representation Learning Algorithms]],​ Richard Golden ​                                                                                           | +
-| 16 | [[http://​arxiv.org/​abs/​1412.6515 ​ | On Distinguishability Criteria for Estimating Generative Models]], Ian Goodfellow ​                                                                                             | +
-| 18 | [[http://​arxiv.org/​abs/​1412.6448 ​ | Embedding Word Similarity with Neural Machine Translation]],​ Felix Hill, Kyunghyun Cho, Sebastien Jean, Coline Devin, and Yoshua Bengio ​                                       | +
-| 20 | [[http://​arxiv.org/​abs/​1412.6622 ​ | Deep metric learning using Triplet network]], Elad Hoffer and Nir Ailon                                                                                                        | +
-| 22 | [[http://​arxiv.org/​abs/​1412.6617 ​ | Understanding Minimum Probability Flow for RBMs Under Various Kinds of Dynamics]], Daniel Jiwoong Im, Ethan Buchman, and Graham Taylor ​                                        | +
-| 23 | [[http://​arxiv.org/​abs/​1504.02462 | A Group Theoretic Perspective on Unsupervised Deep Learning]], Arnab Paul and Suresh Venkatasubramanian ​                                                                       | +
-| 24 | [[http://​arxiv.org/​abs/​1412.7753 ​ | Learning Longer Memory in Recurrent Neural Networks]], Tomas Mikolov, Armand Joulin, Sumit Chopra, Michael Mathieu, and Marc'​Aurelio Ranzato ​                                  | +
-| 25 | [[http://​arxiv.org/​abs/​1412.6418 ​ | Inducing Semantic Representation from Text by Jointly Predicting and Factorizing Relations]],​ Ivan Titov and Ehsan Khoddam ​                                                    | +
-| 27 | [[http://​arxiv.org/​abs/​1410.8516 ​ | NICE: Non-linear Independent Components Estimation]],​ Laurent Dinh, David Krueger, and Yoshua Bengio ​                                                                          | +
-| 28 | [[http://​arxiv.org/​abs/​1412.6583 ​ | Discovering Hidden Factors of Variation in Deep Networks]], Brian Cheung, Jesse Livezey, Arjun Bansal, and Bruno Olshausen ​                                                    | +
-| 29 | [[http://​arxiv.org/​abs/​1412.7004 ​ | Tailoring Word Embeddings for Bilexical Predictions:​ An Experimental Comparison]],​ Pranava Swaroop Madhyastha, Xavier Carreras, and Ariadna Quattoni ​                          | +
-| 30 | [[http://​arxiv.org/​abs/​1412.6881 ​ | On Learning Vector Representations in Hierarchical Label Spaces]], Jinseok Nam and Johannes Fürnkranz ​                                                                         | +
-| 31 | [[http://​arxiv.org/​abs/​1412.6614 ​ | In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning]], Behnam Neyshabur, Ryota Tomioka, and Nathan Srebro ​                           | +
-| 33 | [[http://​arxiv.org/​abs/​1412.6452 ​ | Algorithmic Robustness for Semi-Supervised (ϵ, γ, τ)-Good Metric Learning]], Maria-Irina Nicolae, Marc Sebban, Amaury Habrard, Éric Gaussier, and Massih-Reza Amini            | +
-| 35 | [[http://​arxiv.org/​abs/​1504.00028 | Real-World Font Recognition Using Deep Network and Domain Adaptation]],​ Zhangyang Wang, Jianchao Yang, Hailin Jin, Eli Shechtman, Aseem Agarwala, Jon Brandt, and Thomas Huang | +
-| 36 | [[http://​arxiv.org/​abs/​1412.6514 ​ | Score Function Features for Discriminative Learning]], Majid Janzamin, Hanie Sedghi, and Anima Anandkumar ​                                                                     | +
-| 38 | [[http://​arxiv.org/​abs/​1410.7455 ​ | Parallel training of DNNs with Natural Gradient and Parameter Averaging]],​ Daniel Povey, Xioahui Zhang, and Sanjeev Khudanpur ​                                                 | +
-| 40 | [[http://​arxiv.org/​abs/​1504.04054 | A Generative Model for Deep Convolutional Learning]], Yunchen Pu, Xin Yuan, and Lawrence Carin                                                                                 | +
-| 41 | [[http://​arxiv.org/​abs/​1412.5083 ​ | Random Forests Can Hash]], Qiang Qiu, Guillermo Sapiro, and Alex Bronstein ​                                                                                                    | +
-| 42 | [[http://​arxiv.org/​abs/​1412.2693 ​ | Provable Methods for Training Neural Networks with Sparse Connectivity]],​ Hanie Sedghi, and Anima Anandkumar ​                                                                  | +
-| 43 | [[http://​arxiv.org/​abs/​1411.7676 ​ | Visual Scene Representations:​ sufficiency,​ minimality, invariance and approximation with deep convolutional networks]], Stefano Soatto and Alessandro Chiuso ​                  | +
-| 44 | [[http://​arxiv.org/​abs/​1412.6651 ​ | Deep learning with Elastic Averaging SGD]], Sixin Zhang, Anna Choromanska,​ and Yann LeCun                                                                                      | +
-| 45 | [[http://​arxiv.org/​abs/​1412.6177 ​ | Example Selection For Dictionary Learning]], Tomoki Tsuchida and Garrison Cottrell ​                                                                                            | +
-| 46 | [[http://​arxiv.org/​abs/​1412.6618 ​ | Permutohedral Lattice CNNs]], Martin Kiefel, Varun Jampani, and Peter Gehler ​                                                                                                  | +
-- [[http://​arxiv.org/​abs/​1412.4385 ​ | Unsupervised Domain Adaptation with Feature Embeddings]],​ Yi Yang and Jacob Eisenstein +
-- [[http://​arxiv.org/​abs/​1412.6645 ​ | Weakly Supervised Multi-embeddings Learning of Acoustic Models]], Gabriel Synnaeve and Emmanuel Dupoux+
  
-| [[http://​arxiv.org/​abs/​1412.6830 ​ | Learning Activation Functions to Improve Deep Neural Networks]], Forest Agostinelli,​ Matthew Hoffman, Peter Sadowski, and Pierre Baldi                                  | +  - [[http://​arxiv.org/​abs/​1412.6550|FitNets: Hints for Thin Deep Nets]], Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio 
-| 3 | [[http://​arxiv.org/​abs/​1406.3407 ​ | Restricted Boltzmann Machine for Classification with Hierarchical Correlated Prior]], Gang Chen and Sargur Srihari ​                                                     | +  - [[http://​arxiv.org/​abs/​1406.2989|Techniques for Learning Binary Stochastic Feedforward Neural Networks]], Tapani Raiko, Mathias Berglund, Guillaume Alain, and Laurent Dinh 
-| 4 | [[http://​arxiv.org/​abs/​1407.2538 ​ | Learning Deep Structured Models]], Liang-Chieh Chen, Alexander Schwing, Alan Yuille, and Raquel Urtasun ​                                                                | +  - [[http://​arxiv.org/​abs/​1406.2751|Reweighted Wake-Sleep]],​ Jorg Bornschein and Yoshua Bengio 
-| 5 | [[http://​arxiv.org/​abs/​1412.6277 ​ | N-gram-Based Low-Dimensional Representation for Document Classification]],​ Rémi Lebret and Ronan Collobert ​                                                             | +  - [[http://​arxiv.org/​abs/​1412.7062|Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs]], Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan Yuille 
-| 6 | [[http://​arxiv.org/​abs/​1412.7024 ​ | Low precision arithmetic for deep learning]], Matthieu Courbariaux,​ Yoshua Bengio, and Jean-Pierre David                                                                | +  - [[http://​arxiv.org/​abs/​1412.7755|Multiple Object Recognition with Visual Attention]],​ Jimmy Ba, Volodymyr Mnih, and Koray Kavukcuoglu 
-| 7 | [[http://​arxiv.org/​abs/​1412.2302 ​ | Theano-based Large-Scale Visual Recognition with Multiple GPUs]], Weiguang Ding, Ruoyan Wang, Fei Mao, and Graham Taylor ​                                               | +  - [[http://​arxiv.org/​abs/​1411.3784|Deep Narrow Boltzmann Machines are Universal Approximators]],​ Guido Montufar 
-| 8 | [[http://​arxiv.org/​abs/​1412.6568 ​ | Improving zero-shot learning by mitigating the hubness problem]], Georgiana Dinu and Marco Baroni ​                                                                      | +  - [[http://​arxiv.org/​abs/​1412.7659|Transformation Properties of Learned Visual Representations]],​ Taco Cohen and Max Welling 
-| 9 | [[http://​arxiv.org/​abs/​1412.5836 ​ | Incorporating Both Distributional and Relational Semantics in Word Representations]],​ Daniel Fried and Kevin Duh                                                        | +  - [[http://​arxiv.org/​abs/​1412.7028|Joint RNN-Based Greedy Parsing and Word Composition]],​ Joël Legrand and Ronan Collobert 
-| 10 | [[http://​arxiv.org/​abs/​1412.6581 ​ | Variational Recurrent Auto-Encoders]],​ Otto Fabius and Joost van Amersfoort ​                                                                                            | +  - [[http://​arxiv.org/​abs/​1412.6980|Adam:​ A Method for Stochastic Optimization]],​ Jimmy Ba and Diederik Kingma 
-| 11 | [[http://​arxiv.org/​abs/​1412.7155 ​ | Learning Compact Convolutional Neural Networks with Nested Dropout]], Chelsea Finn, Lisa Anne Hendricks, and Trevor Darrell ​                                            | +  - [[http://​arxiv.org/​abs/​1409.0473|Neural Machine Translation by Jointly Learning to Align and Translate]],​ Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio 
-| 13 | [[http://​arxiv.org/​abs/​1412.3708 ​ | Compact Part-Based Image Representations:​ Extremal Competition and Overgeneralization]],​ Marc Goessling and Yali Amit                                                   | +  - [[http://​arxiv.org/​abs/​1406.3269|Scheduled denoising autoencoders]],​ Krzysztof Geras and Charles Sutton 
-| 15 | [[http://​arxiv.org/​abs/​1504.02518 | Unsupervised Feature Learning from Temporal Data]], Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, and Yann LeCun                                            | +  - [[http://​arxiv.org/​abs/​1412.6575|Embedding Entities and Relations for Learning and Inference in Knowledge Bases]], Bishan Yang, Scott Yih, Xiaodong He, Jianfeng Gao, and Li Deng 
-| 16 | [[http://​arxiv.org/​abs/​1412.6567 ​ | Classifier with Hierarchical Topographical Maps as Internal Representation]],​ Pitoyo Hartono, Paul Hollensen, and Thomas Trappenberg ​                                   | +  - [[http://​arxiv.org/​abs/​1412.6626|The local low-dimensionality of natural images]], Olivier Henaff, Johannes Balle, Neil Rabinowitz, and Eero Simoncelli 
-| 18 | [[http://​arxiv.org/​abs/​1412.5673 ​ | Entity-Augmented Distributional Semantics for Discourse Relations]],​ Yangfeng Ji and Jacob Eisenstein ​                                                                  | +  - [[http://​arxiv.org/​abs/​1412.6572|Explaining and Harnessing Adversarial Examples]], Ian Goodfellow, Jon Shlens, and Christian Szegedy 
-| 20 | [[http://​arxiv.org/​abs/​1412.5474 ​ | Flattened Convolutional Neural Networks for Feedforward Acceleration]],​ Jonghoon Jin, Aysegul Dundar, and Eugenio Culurciello ​                                          | +  - [[http://​arxiv.org/​abs/​1412.6577|Modeling Compositionality with Multiplicative Recurrent Neural Networks]], Ozan Irsoy and Claire Cardie 
-| 22 | [[http://​arxiv.org/​abs/​1504.02902 | Gradual Training Method for Denoising Auto Encoders]], Alexander Kalmanovich and Gal Chechik ​                                                                           | +  - [[http://​arxiv.org/​abs/​1409.1556|Very Deep Convolutional Networks for Large-Scale Image Recognition]],​ Karen Simonyan and Andrew Zisserman 
-| 23 | [[http://​arxiv.org/​abs/​1411.1045 ​ | Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet]], Matthias Kümmerer, Lucas Theis, and Matthias Bethge ​                                 | +  - [[http://​arxiv.org/​abs/​1412.6553|Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition]],​ Vadim Lebedev, Yaroslav Ganin, Victor Lempitsky, Maksim Rakhuba, and Ivan Oseledets 
-| 24 | [[http://​arxiv.org/​abs/​1412.7525 ​ | Difference Target Propagation]],​ Dong-Hyun Lee, Saizheng Zhang, Asja Fischer, Antoine Biard, and Yoshua Bengio ​                                                         | +  -[[http://​arxiv.org/​abs/​1412.6632|Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)]], Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, and Alan Yuille 
-| 25 | [[http://​arxiv.org/​abs/​1411.3815 ​ | Predictive encoding of contextual relationships for perceptual inference, interpolation and prediction]],​ Mingmin Zhao, Chengxu Zhuang, Yizhou Wang, and Tai Sing Lee   | +  -  [[http://​arxiv.org/​abs/​1412.5903|Deep Structured Output Learning for Unconstrained Text Recognition]],​ Max Jaderberg, Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman 
-| 27 | [[http://​arxiv.org/​abs/​1412.6249 ​ | Purine: A Bi-Graph based deep learning framework]],​ Min Lin, Shuo Li, Xuan Luo, and Shuicheng Yan                                                                       | +  - [[http://​arxiv.org/​abs/​1402.3337|Zero-bias autoencoders and the benefits of co-adapting features]], Kishore Konda, Roland Memisevic, and David Krueger 
-| 28 | [[http://​arxiv.org/​abs/​1504.01989 | Pixel-wise Deep Learning for Contour Detection]],​ Jyh-Jing Hwang and Tyng-Luh Liu                                                                                       | +  - [[http://​arxiv.org/​abs/​1412.6598|Automatic Discovery and Optimization of Parts for Image Classification]],​ Sobhan Naderi Parizi, Andrea Vedaldi, Andrew Zisserman, and Pedro Felzenszwalb 
-| 29 | [[http://​arxiv.org/​abs/​1412.5335 ​ | Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews]], Grégoire Mesnil, Tomas Mikolov, Marc'​Aurelio Ranzato, and Yoshua Bengio ​| +  - [[http://​arxiv.org/​abs/​1410.1165|Understanding Locally Competitive Networks]], Rupesh Srivastava, Jonathan Masci, Faustino Gomez, and Juergen Schmidhuber 
-| 30 | [[http://​arxiv.org/​abs/​1503.08873 | Fast Label Embeddings for Extremely Large Output Spaces]], Paul Mineiro and Nikos Karampatziakis ​                                                                       | +  - [[http://​arxiv.org/​abs/​1412.6334|Leveraging Monolingual Data for Crosslingual Compositional Word Representations]],​ Hubert Soyer, Pontus Stenetorp, and Akiko Aizawa 
-| 31 | [[http://​arxiv.org/​abs/​1412.6597 ​ | An Analysis of Unsupervised Pre-training in Light of Recent Advances]], Tom Paine, Pooya Khorrami, Wei Han, and Thomas Huang                                            | +  - [[http://​arxiv.org/​abs/​1412.6564|Move Evaluation in Go Using Deep Convolutional Neural Networks]], Chris Maddison, Aja Huang, Ilya Sutskever, and David Silver 
-| 33 | [[http://​arxiv.org/​abs/​1412.7144 ​ | Fully Convolutional Multi-Class Multiple Instance Learning]], Deepak Pathak, Evan Shelhamer, Jonathan Long, and Trevor Darrell ​                                         | +  - [[http://​arxiv.org/​abs/​1412.7580|Fast Convolutional Nets With fbfft: A GPU Performance Evaluation]],​ Nicolas Vasilache, Jeff Johnson, Michael Mathieu, Soumith Chintala, Serkan Piantino, and Yann LeCun 
-| 35 | [[http://​arxiv.org/​abs/​1504.02485 | What Do Deep CNNs Learn About Objects?]], Xingchao Peng, Baochen Sun, Karim Ali, and Kate Saenko ​                                                                       | +  - [[http://​arxiv.org/​abs/​1412.6623|Word Representations via Gaussian Embedding]],​ Luke Vilnis and Andrew McCallum 
-| 36 | [[http://​arxiv.org/​abs/​1412.6134 ​ | Representation using the Weyl Transform]],​ Qiang Qiu, Andrew Thompson, Robert Calderbank, and Guillermo Sapiro ​                                                         | +  - [[http://​arxiv.org/​abs/​1412.6544|Qualitatively characterizing neural network optimization problems]], Ian Goodfellow and Oriol Vinyals 
-| 38 | [[http://​arxiv.org/​abs/​1412.7210 ​ | Denoising autoencoder with modulated lateral connections learns invariant representations of natural images]], Antti Rasmus, Harri Valpola, and Tapani Raiko            | +  - [[http://​arxiv.org/​abs/​1410.3916|Memory Networks]], Jason Weston, Sumit Chopra, and Antoine Bordes 
-| 40 | [[http://​arxiv.org/​abs/​1412.5068 ​ | Towards Deep Neural Network Architectures Robust to Adversarial Examples]], Shixiang Gu and Luca Rigazio ​                                                               | +  - [[http://​arxiv.org/​abs/​1412.6296|Generative Modeling of Convolutional Neural Networks]], Jifeng Dai, Yang Lu, and Ying-Nian Wu 
-| 41 | [[http://​arxiv.org/​abs/​1412.6615 ​ | Explorations on high dimensional landscapes]],​ Levent Sagun, Ugur Guney, and Yann LeCun                                                                                 | +  - [[http://​arxiv.org/​abs/​1412.7489|A Unified Perspective on Multi-Domain and Multi-Task Learning]], Yongxin Yang and Timothy Hospedales 
-| 42 | [[http://​arxiv.org/​abs/​1412.7009 ​ | Generative Class-conditional Autoencoders]],​ Jan Rudy and Graham Taylor ​                                                                                                | +  - [[http://​arxiv.org/​abs/​1412.6856|Object detectors emerge in Deep Scene CNNs]], Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba 
-| 43 | [[http://​arxiv.org/​abs/​1412.7054 ​ | Attention for Fine-Grained Categorization]],​ Pierre Sermanet, Andrea Frome, and Esteban Real                                                                            | + 
-| 44 | [[http://​arxiv.org/​abs/​1412.6574 ​ | A Baseline for Visual Instance Retrieval with Deep Convolutional Networks]], Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, and Stefan Carlsson ​                 | + 
-| 45 | [[http://​arxiv.org/​abs/​1412.6607 ​ | Visual Scene Representation:​ Scaling and Occlusion]],​ Stefano Soatto, Jingming Dong, and Nikolaos Karianakis ​                                                           | +====Workshop Papers==== 
-| 46 | [[http://​arxiv.org/​abs/​1412.7479 ​ | Deep networks with large output spaces]], Sudheendra Vijayanarasimhan,​ Jon Shlens, Jay Yagnik, and Rajat Monga                                                          | + 
-| 47 | [[http://​arxiv.org/​abs/​1412.7091 ​ | Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets]], Pascal Vincent ​                                                            | +  - [[http://​arxiv.org/​abs/​1412.7272 ​ | Learning Non-deterministic Representations with Energy-based Ensembles]],​ Maruan Al-Shedivat,​ Emre Neftci, and Gert Cauwenberghs 
-| 49 | [[http://​arxiv.org/​abs/​1412.6563 ​ | Self-informed neural network structure learning]], David Warde-Farley,​ Andrew Rabinovich, and Dragomir Anguelov ​                                                        |+  - [[http://​arxiv.org/​abs/​1412.7063 ​ | Diverse Embedding Neural Network Language Models]], Kartik Audhkhasi, Abhinav Sethy, and Bhuvana Ramabhadran 
 +  - [[http://​arxiv.org/​abs/​1412.6599 ​ | Hot Swapping for Online Adaptation of Optimization Hyperparameters]],​ Kevin Bache, Dennis Decoste, and Padhraic Smyth 
 +  - [[http://​arxiv.org/​abs/​1412.7156 ​ | Representation Learning for cold-start recommendation]],​ Gabriella Contardo, Ludovic Denoyer, and Thierry Artieres 
 +  - [[http://​arxiv.org/​abs/​1406.2080 ​ | Training Convolutional Networks with Noisy Labels]], Sainbayar Sukhbaatar, Joan Bruna, Manohar Paluri, Lubomir Bourdev, and Rob Fergus 
 +  - [[http://​arxiv.org/​abs/​1412.6806 ​ | Striving for Simplicity: ​ The All Convolutional Net]], Alexey Dosovitskiy,​ Jost Tobias Springenberg,​ Thomas Brox, and Martin Riedmiller 
 +  - [[http://​arxiv.org/​abs/​1412.7110 ​ | Learning linearly separable features for speech recognition using convolutional neural networks]], Dimitri Palaz, Mathew Magimai Doss, and Ronan Collobert 
 +  - [[http://​arxiv.org/​abs/​1412.6596 ​ | Training Deep Neural Networks on Noisy Labels with Bootstrapping]],​ Scott Reed, Honglak Lee, Dragomir Anguelov, Christian Szegedy, Dumitru Erhan, and Andrew Rabinovich 
 +  - [[http://​arxiv.org/​abs/​1412.5896 ​ | On the Stability of Deep Networks]], Raja Giryes, Guillermo Sapiro, and Alex Bronstein 
 +  - [[http://​arxiv.org/​abs/​1412.7022 ​ | Audio source separation with Discriminative Scattering Networks ]], Joan Bruna, Yann LeCun, and Pablo Sprechmann 
 +  - [[http://​arxiv.org/​abs/​1412.8419 ​ | Simple Image Description Generator via a Linear Phrase-Based Model]], Pedro Pinheiro, Rémi Lebret, and Ronan Collobert 
 +  - [[http://​arxiv.org/​abs/​1412.5744 ​ | Stochastic Descent Analysis of Representation Learning Algorithms]],​ Richard Golden 
 +  - [[http://​arxiv.org/​abs/​1412.6515 ​ | On Distinguishability Criteria for Estimating Generative Models]], Ian Goodfellow 
 +  - [[http://​arxiv.org/​abs/​1412.6448 ​ | Embedding Word Similarity with Neural Machine Translation]],​ Felix Hill, Kyunghyun Cho, Sebastien Jean, Coline Devin, and Yoshua Bengio 
 +  - [[http://​arxiv.org/​abs/​1412.6622 ​ | Deep metric learning using Triplet network]], Elad Hoffer and Nir Ailon 
 +  - [[http://​arxiv.org/​abs/​1412.6617 ​ | Understanding Minimum Probability Flow for RBMs Under Various Kinds of Dynamics]], Daniel Jiwoong Im, Ethan Buchman, and Graham Taylor 
 +  - [[http://​arxiv.org/​abs/​1504.02462 | A Group Theoretic Perspective on Unsupervised Deep Learning]], Arnab Paul and Suresh Venkatasubramanian 
 +  - [[http://​arxiv.org/​abs/​1412.7753 ​ | Learning Longer Memory in Recurrent Neural Networks]], Tomas Mikolov, Armand Joulin, Sumit Chopra, Michael Mathieu, and Marc'​Aurelio Ranzato 
 +  - [[http://​arxiv.org/​abs/​1412.6418 ​ | Inducing Semantic Representation from Text by Jointly Predicting and Factorizing Relations]],​ Ivan Titov and Ehsan Khoddam 
 +  - [[http://​arxiv.org/​abs/​1410.8516 ​ | NICE: Non-linear Independent Components Estimation]],​ Laurent Dinh, David Krueger, and Yoshua Bengio 
 +  - [[http://​arxiv.org/​abs/​1412.6583 ​ | Discovering Hidden Factors of Variation in Deep Networks]], Brian Cheung, Jesse Livezey, Arjun Bansal, and Bruno Olshausen 
 +  - [[http://​arxiv.org/​abs/​1412.7004 ​ | Tailoring Word Embeddings for Bilexical Predictions:​ An Experimental Comparison]],​ Pranava Swaroop Madhyastha, Xavier Carreras, and Ariadna Quattoni 
 +  - [[http://​arxiv.org/​abs/​1412.6881 ​ | On Learning Vector Representations in Hierarchical Label Spaces]], Jinseok Nam and Johannes Fürnkranz 
 +  - [[http://​arxiv.org/​abs/​1412.6614 ​ | In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning]], Behnam Neyshabur, Ryota Tomioka, and Nathan Srebro 
 +  - [[http://​arxiv.org/​abs/​1412.6452 ​ | Algorithmic Robustness for Semi-Supervised (ϵ, γ, τ)-Good Metric Learning]], Maria-Irina Nicolae, Marc Sebban, Amaury Habrard, Éric Gaussier, and Massih-Reza Amini 
 +  - [[http://​arxiv.org/​abs/​1504.00028 | Real-World Font Recognition Using Deep Network and Domain Adaptation]],​ Zhangyang Wang, Jianchao Yang, Hailin Jin, Eli Shechtman, Aseem Agarwala, Jon Brandt, and Thomas Huang 
 +  - [[http://​arxiv.org/​abs/​1412.6514 ​ | Score Function Features for Discriminative Learning]], Majid Janzamin, Hanie Sedghi, and Anima Anandkumar 
 +  - [[http://​arxiv.org/​abs/​1410.7455 ​ | Parallel training of DNNs with Natural Gradient and Parameter Averaging]],​ Daniel Povey, Xioahui Zhang, and Sanjeev Khudanpur 
 +  - [[http://​arxiv.org/​abs/​1504.04054 | A Generative Model for Deep Convolutional Learning]], Yunchen Pu, Xin Yuan, and Lawrence Carin 
 +  - [[http://​arxiv.org/​abs/​1412.5083 ​ | Random Forests Can Hash]], Qiang Qiu, Guillermo Sapiro, and Alex Bronstein 
 +  - [[http://​arxiv.org/​abs/​1412.2693 ​ | Provable Methods for Training Neural Networks with Sparse Connectivity]],​ Hanie Sedghi, and Anima Anandkumar 
 +  - [[http://​arxiv.org/​abs/​1411.7676 ​ | Visual Scene Representations:​ sufficiency,​ minimality, invariance and approximation with deep convolutional networks]], Stefano Soatto and Alessandro Chiuso ​                  | 
 +  - [[http://​arxiv.org/​abs/​1412.6651 ​ | Deep learning with Elastic Averaging SGD]], Sixin Zhang, Anna Choromanska,​ and Yann LeCun 
 +  - [[http://​arxiv.org/​abs/​1412.6177 ​ | Example Selection For Dictionary Learning]], Tomoki Tsuchida and Garrison Cottrell 
 +  - [[http://​arxiv.org/​abs/​1412.6618 ​ | Permutohedral Lattice CNNs]], Martin Kiefel, Varun Jampani, and Peter Gehler 
 +  - [[http://​arxiv.org/​abs/​1412.4385 ​ | Unsupervised Domain Adaptation with Feature Embeddings]],​ Yi Yang and Jacob Eisenstein 
 +  - [[http://​arxiv.org/​abs/​1412.6645 ​ | Weakly Supervised Multi-embeddings Learning of Acoustic Models]], Gabriel Synnaeve and Emmanuel Dupoux 
 + 
 +  - [[http://​arxiv.org/​abs/​1412.6830 ​ | Learning Activation Functions to Improve Deep Neural Networks]], Forest Agostinelli,​ Matthew Hoffman, Peter Sadowski, and Pierre Baldi                                  | 
 +  ​- ​[[http://​arxiv.org/​abs/​1406.3407 ​ | Restricted Boltzmann Machine for Classification with Hierarchical Correlated Prior]], Gang Chen and Sargur Srihari 
 +  ​- ​[[http://​arxiv.org/​abs/​1407.2538 ​ | Learning Deep Structured Models]], Liang-Chieh Chen, Alexander Schwing, Alan Yuille, and Raquel Urtasun 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.6277 ​ | N-gram-Based Low-Dimensional Representation for Document Classification]],​ Rémi Lebret and Ronan Collobert 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.7024 ​ | Low precision arithmetic for deep learning]], Matthieu Courbariaux,​ Yoshua Bengio, and Jean-Pierre David 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.2302 ​ | Theano-based Large-Scale Visual Recognition with Multiple GPUs]], Weiguang Ding, Ruoyan Wang, Fei Mao, and Graham Taylor 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.6568 ​ | Improving zero-shot learning by mitigating the hubness problem]], Georgiana Dinu and Marco Baroni 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.5836 ​ | Incorporating Both Distributional and Relational Semantics in Word Representations]],​ Daniel Fried and Kevin Duh 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.6581 ​ | Variational Recurrent Auto-Encoders]],​ Otto Fabius and Joost van Amersfoort 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.7155 ​ | Learning Compact Convolutional Neural Networks with Nested Dropout]], Chelsea Finn, Lisa Anne Hendricks, and Trevor Darrell 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.3708 ​ | Compact Part-Based Image Representations:​ Extremal Competition and Overgeneralization]],​ Marc Goessling and Yali Amit 
 +  ​- ​[[http://​arxiv.org/​abs/​1504.02518 | Unsupervised Feature Learning from Temporal Data]], Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, and Yann LeCun 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.6567 ​ | Classifier with Hierarchical Topographical Maps as Internal Representation]],​ Pitoyo Hartono, Paul Hollensen, and Thomas Trappenberg 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.5673 ​ | Entity-Augmented Distributional Semantics for Discourse Relations]],​ Yangfeng Ji and Jacob Eisenstein 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.5474 ​ | Flattened Convolutional Neural Networks for Feedforward Acceleration]],​ Jonghoon Jin, Aysegul Dundar, and Eugenio Culurciello 
 +  ​- ​[[http://​arxiv.org/​abs/​1504.02902 | Gradual Training Method for Denoising Auto Encoders]], Alexander Kalmanovich and Gal Chechik 
 +  ​- ​[[http://​arxiv.org/​abs/​1411.1045 ​ | Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet]], Matthias Kümmerer, Lucas Theis, and Matthias Bethge 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.7525 ​ | Difference Target Propagation]],​ Dong-Hyun Lee, Saizheng Zhang, Asja Fischer, Antoine Biard, and Yoshua Bengio 
 +  ​- ​[[http://​arxiv.org/​abs/​1411.3815 ​ | Predictive encoding of contextual relationships for perceptual inference, interpolation and prediction]],​ Mingmin Zhao, Chengxu Zhuang, Yizhou Wang, and Tai Sing Lee 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.6249 ​ | Purine: A Bi-Graph based deep learning framework]],​ Min Lin, Shuo Li, Xuan Luo, and Shuicheng Yan 
 +  ​- ​[[http://​arxiv.org/​abs/​1504.01989 | Pixel-wise Deep Learning for Contour Detection]],​ Jyh-Jing Hwang and Tyng-Luh Liu 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.5335 ​ | Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews]], Grégoire Mesnil, Tomas Mikolov, Marc'​Aurelio Ranzato, and Yoshua Bengio 
 +  ​- ​[[http://​arxiv.org/​abs/​1503.08873 | Fast Label Embeddings for Extremely Large Output Spaces]], Paul Mineiro and Nikos Karampatziakis 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.6597 ​ | An Analysis of Unsupervised Pre-training in Light of Recent Advances]], Tom Paine, Pooya Khorrami, Wei Han, and Thomas Huang 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.7144 ​ | Fully Convolutional Multi-Class Multiple Instance Learning]], Deepak Pathak, Evan Shelhamer, Jonathan Long, and Trevor Darrell 
 +  ​- ​[[http://​arxiv.org/​abs/​1504.02485 | What Do Deep CNNs Learn About Objects?]], Xingchao Peng, Baochen Sun, Karim Ali, and Kate Saenko 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.6134 ​ | Representation using the Weyl Transform]],​ Qiang Qiu, Andrew Thompson, Robert Calderbank, and Guillermo Sapiro 
 +  -[[http://​arxiv.org/​abs/​1412.7210 ​ | Denoising autoencoder with modulated lateral connections learns invariant representations of natural images]], Antti Rasmus, Harri Valpola, and Tapani Raiko 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.5068 ​ | Towards Deep Neural Network Architectures Robust to Adversarial Examples]], Shixiang Gu and Luca Rigazio 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.6615 ​ | Explorations on high dimensional landscapes]],​ Levent Sagun, Ugur Guney, and Yann LeCun 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.7009 ​ | Generative Class-conditional Autoencoders]],​ Jan Rudy and Graham Taylor 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.7054 ​ | Attention for Fine-Grained Categorization]],​ Pierre Sermanet, Andrea Frome, and Esteban Real 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.6574 ​ | A Baseline for Visual Instance Retrieval with Deep Convolutional Networks]], Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, and Stefan Carlsson 
 +  ​-  ​[[http://​arxiv.org/​abs/​1412.6607 ​ | Visual Scene Representation:​ Scaling and Occlusion]],​ Stefano Soatto, Jingming Dong, and Nikolaos Karianakis 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.7479 ​ | Deep networks with large output spaces]], Sudheendra Vijayanarasimhan,​ Jon Shlens, Jay Yagnik, and Rajat Monga 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.7091 ​ | Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets]], Pascal Vincent 
 +  ​- ​[[http://​arxiv.org/​abs/​1412.6563 ​ | Self-informed neural network structure learning]], David Warde-Farley,​ Andrew Rabinovich, and Dragomir Anguelov