ICLR 2016:San Juan, Puerto Rico

International Conference on Learning Representations, May 2 - 4, 2016, Caribe Hilton, San Juan, Puerto Rico

Paper Num: 80 || Session Num: 2

• Oral Presentations 15
• Poster Presentations 65

Oral Presentations 15

1. Neural Programmer-Interpreters

【Paper Link】 【Pages】:

【Authors】: Scott Reed, Nando de Freitas

【Abstract】:

【Keywords】:

2. Regularizing RNNs by Stabilizing Activations

【Paper Link】 【Pages】:

【Authors】: David Krueger, Roland Memisevic

【Abstract】:

【Keywords】:

3. BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies

【Paper Link】 【Pages】:

【Authors】: Shihao Ji, Swaminathan Vishwanathan, Nadathur Satish, Michael Anderson, Pradeep Dubey

【Abstract】:

【Keywords】:

4. The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations

【Paper Link】 【Pages】:

【Authors】: Felix Hill, Antoine Bordes, Sumit Chopra, Jason Weston

【Abstract】:

【Keywords】:

5. Towards Universal Paraphrastic Sentence Embeddings

【Paper Link】 【Pages】:

【Authors】: John Wieting, Mohit Bansal, Kevin Gimpel, Karen Livescu

【Abstract】:

【Keywords】:

6. Convergent Learning: Do different neural networks learn the same representations?

【Paper Link】 【Pages】:

【Authors】: Yixuan Li, Jason Yosinski, Jeff Clune, Hod Lipson, John Hopcroft

【Abstract】:

【Keywords】:

7. Net2Net: Accelerating Learning via Knowledge Transfer

【Paper Link】 【Pages】:

【Authors】: Tianqi Chen, Ian Goodfellow, Jon Shlens

【Abstract】:

【Keywords】:

8. Variational Gaussian Process

【Paper Link】 【Pages】:

【Authors】: Dustin Tran, Rajesh Ranganath, David Blei

【Abstract】:

【Keywords】:

9. The Variational Fair Autoencoder

【Paper Link】 【Pages】:

【Authors】: Christos Louizos, Kevin Swersky, Yujia Li, Max Welling, Richard Zemel

【Abstract】:

【Keywords】:

10. A note on the evaluation of generative models

【Paper Link】 【Pages】:

【Authors】: Lucas Theis, Aäron van den Oord, Matthias Bethge

【Abstract】:

【Keywords】:

11. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

【Paper Link】 【Pages】:

【Authors】: Song Han, Huizi Mao, Bill Dally

【Abstract】:

【Keywords】:

12. Neural Networks with Few Multiplications

【Paper Link】 【Pages】:

【Authors】: Zhouhan Lin, Matthieu Courbariaux, Roland Memisevic, Yoshua Bengio

【Abstract】:

【Keywords】:

13. Order-Embeddings of Images and Language

【Paper Link】 【Pages】:

【Authors】: Ivan Vendrov, Ryan Kiros, Sanja Fidler, Raquel Urtasun

【Abstract】:

【Keywords】:

14. Generating Images from Captions with Attention

【Paper Link】 【Pages】:

【Authors】: Elman Mansimov, Emilio Parisotto, Jimmy Ba, Ruslan Salakhutdinov

【Abstract】:

【Keywords】:

15. Density Modeling of Images using a Generalized Normalization Transformation

【Paper Link】 【Pages】:

【Authors】: Johannes Ballé, Valero Laparra, Eero Simoncelli

【Abstract】:

【Keywords】:

Poster Presentations 65

16. Multi-Scale Context Aggregation by Dilated Convolutions

【Paper Link】 【Pages】:

【Authors】: Fisher Yu, Vladlen Koltun

【Abstract】:

【Keywords】:

17. Learning to Diagnose with LSTM Recurrent Neural Networks

【Paper Link】 【Pages】:

【Authors】: Zachary Lipton, David Kale, Charles Elkan, Randall Wetzel

【Abstract】:

【Keywords】:

18. Prioritized Experience Replay

【Paper Link】 【Pages】:

【Authors】: Tom Schaul, John Quan, Ioannis Antonoglou, David Silver

【Abstract】:

【Keywords】:

19. Importance Weighted Autoencoders

【Paper Link】 【Pages】:

【Authors】: Yuri Burda, Ruslan Salakhutdinov, Roger Grosse

【Abstract】:

【Keywords】:

20. Variationally Auto-Encoded Deep Gaussian Processes

【Paper Link】 【Pages】:

【Authors】: Zhenwen Dai, Andreas Damianou, Javier Gonzalez, Neil Lawrence

【Abstract】:

【Keywords】:

21. Training Convolutional Neural Networks with Low-rank Filters for Efficient Image Classification

【Paper Link】 【Pages】:

【Authors】: Yani Ioannou, Duncan Robertson, Jamie Shotton, roberto Cipolla, Antonio Criminisi, Jamie Shotton

【Abstract】:

【Keywords】:

22. Reducing Overfitting in Deep Networks by Decorrelating Representations

【Paper Link】 【Pages】:

【Authors】: Michael Cogswell, Faruk Ahmed, Ross Girshick, Larry Zitnick, Dhruv Batra

【Abstract】:

【Keywords】:

23. Pushing the Boundaries of Boundary Detection using Deep Learning

【Paper Link】 【Pages】:

【Authors】: Iasonas Kokkinos

【Abstract】:

【Keywords】:

24. Reasoning about Entailment with Neural Attention

【Paper Link】 【Pages】:

【Authors】: Tim Rocktäschel, Edward Grefenstette, Karl Moritz Hermann, Tomáš Kočiský, Phil Blunsom

【Abstract】:

【Keywords】:

25. Convolutional Neural Networks With Low-rank Regularization

【Paper Link】 【Pages】:

【Authors】: Cheng Tai, Tong Xiao, Yi Zhang, Xiaogang Wang, Weinan E

【Abstract】:

【Keywords】:

26. Unifying distillation and privileged information

【Paper Link】 【Pages】:

【Authors】: David Lopez-Paz, Leon Bottou, Bernhard Schölkopf, Vladimir Vapnik

【Abstract】:

【Keywords】:

27. Particular object retrieval with integral max-pooling of CNN activations

【Paper Link】 【Pages】:

【Authors】: Giorgos Tolias, Ronan Sicre, Hervé Jégou

【Abstract】:

【Keywords】:

28. All you need is a good init

【Paper Link】 【Pages】:

【Authors】: Dmytro Mishkin, Jiri Matas

【Abstract】:

【Keywords】:

29. Bayesian Representation Learning with Oracle Constraints

【Paper Link】 【Pages】:

【Authors】: Theofanis Karaletsos, Serge Belongie, Gunnar Rätsch

【Abstract】:

【Keywords】:

30. Neural Programmer: Inducing Latent Programs with Gradient Descent

【Paper Link】 【Pages】:

【Authors】: Arvind Neelakantan, Quoc Le, Ilya Sutskever

【Abstract】:

【Keywords】:

31. SparkNet: Training Deep Networks in Spark

【Paper Link】 【Pages】:

【Authors】: Philipp Moritz, Robert Nishihara, Ion Stoica, Michael Jordan

【Abstract】:

【Keywords】:

32. Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

【Paper Link】 【Pages】:

【Authors】: Jost Tobias Springenberg

【Abstract】:

【Keywords】:

33. MuProp: Unbiased Backpropagation For Stochastic Neural Networks

【Paper Link】 【Pages】:

【Authors】: Shixiang Gu, Sergey Levine, Ilya Sutskever, Andriy Mnih

【Abstract】:

【Keywords】:

34. Data Representation and Compression Using Linear-Programming Approximations

【Paper Link】 【Pages】:

【Authors】: Hristo Paskov, John Mitchell, Trevor Hastie

【Abstract】:

【Keywords】:

35. Diversity Networks

【Paper Link】 【Pages】:

【Authors】: Zelda Mariet, Suvrit Sra

【Abstract】:

【Keywords】:

36. Deep Reinforcement Learning in Parameterized Action Space

【Paper Link】 【Pages】:

【Authors】: Matthew Hausknecht, Peter Stone

【Abstract】:

【Keywords】:

37. Learning VIsual Predictive Models of Physics for Playing Billiards

【Paper Link】 【Pages】:

【Authors】: Katerina Fragkiadaki, Pulkit Agrawal, Sergey Levine, Jitendra Malik

【Abstract】:

【Keywords】:

38. Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

【Paper Link】 【Pages】:

【Authors】: Jason Weston, Antoine Bordes, Sumit Chopra, Sasha Rush, Bart van Merrienboer, Armand Joulin, Tomas Mikolov

【Abstract】:

【Keywords】:

39. Evaluating Prerequisite Qualities for Learning End-to-end Dialog Systems

【Paper Link】 【Pages】:

【Authors】: Jesse Dodge, Andreea Gane, Xiang Zhang, Antoine Bordes, Sumit Chopra, Alexander Miller, Arthur Szlam, Jason Weston

【Abstract】:

【Keywords】:

40. Better Computer Go Player with Neural Network and Long-term Prediction

【Paper Link】 【Pages】:

【Authors】: Yuandong Tian, Yan Zhu

【Abstract】:

【Keywords】:

41. Distributional Smoothing with Virtual Adversarial Training

【Paper Link】 【Pages】:

【Authors】: Takeru Miyato, Shin-ichi Maeda, Masanori Koyama, Ken Nakae, Shin Ishii

【Abstract】:

【Keywords】:

42. Multi-task Sequence to Sequence Learning

【Paper Link】 【Pages】:

【Authors】: Minh-Thang Luong, Quoc Le, Ilya Sutskever, Oriol Vinyals, Lukasz Kaiser

【Abstract】:

【Keywords】:

43. A Test of Relative Similarity for Model Selection in Generative Models

【Paper Link】 【Pages】:

【Authors】: Eugene Belilovsky, Wacha Bounliphone, Matthew Blaschko, Ioannis Antonoglou, Arthur Gretton

【Abstract】:

【Keywords】:

44. Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications

【Paper Link】 【Pages】:

【Authors】: Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo, Taelim Choi, Lu Yang, Dongjun Shin

【Abstract】:

【Keywords】:

45. Session-based recommendations with recurrent neural networks

【Paper Link】 【Pages】:

【Authors】: Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, Domonkos Tikk

【Abstract】:

【Keywords】:

46. Continuous control with deep reinforcement learning

【Paper Link】 【Pages】:

【Authors】: Timothy Lillicrap, Jonathan Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, Daan Wierstra

【Abstract】:

【Keywords】:

47. Recurrent Gaussian Processes

【Paper Link】 【Pages】:

【Authors】: César Lincoln Mattos, Zhenwen Dai, Andreas Damianou, Jeremy Forth, Guilherme Barreto, Neil Lawrence

【Abstract】:

【Keywords】:

48. Modeling Visual Representations:Defining Properties and Deep Approximations

【Paper Link】 【Pages】:

【Authors】: Stefano Soatto, Alessandro Chiuso

【Abstract】:

【Keywords】:

49. Auxiliary Image Regularization for Deep CNNs with Noisy Labels

【Paper Link】 【Pages】:

【Authors】: Samaneh Azadi, Jiashi Feng, Stefanie Jegelka, Trevor Darrell

【Abstract】:

【Keywords】:

50. Policy Distillation

【Paper Link】 【Pages】:

【Authors】: Andrei Rusu, Sergio Gomez, Caglar Gulcehre, Guillaume Desjardins, James Kirkpatrick, Razvan Pascanu, Volodymyr Mnih, Koray Kavukcuoglu, Raia Hadsell

【Abstract】:

【Keywords】:

51. Neural Random-Access Machines

【Paper Link】 【Pages】:

【Authors】: Karol Kurach, Marcin Andrychowicz, Ilya Sutskever

【Abstract】:

【Keywords】:

52. Gated Graph Sequence Neural Networks

【Paper Link】 【Pages】:

【Authors】: Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard Zemel, CIFAR

【Abstract】:

【Keywords】:

53. Metric Learning with Adaptive Density Discrimination

【Paper Link】 【Pages】:

【Authors】: Oren Rippel, Manohar Paluri, Piotr Dollar, Lubomir Bourdev

【Abstract】:

【Keywords】:

54. Censoring Representations with an Adversary

【Paper Link】 【Pages】:

【Authors】: Harrison Edwards, Amos Storkey

【Abstract】:

【Keywords】:

55. Variable Rate Image Compression with Recurrent Neural Networks

【Paper Link】 【Pages】:

【Authors】: George Toderici, Sean O'Malley, Damien Vincent, Sung Jin Hwang, Michele Covell, Shumeet Baluja, Rahul Sukthankar, David Minnen

【Abstract】:

【Keywords】:

56. Delving Deeper into Convolutional Networks for Learning Video Representations

【Paper Link】 【Pages】:

【Authors】: Nicolas Ballas, Li Yao, Pal Chris, Aaron Courville

【Abstract】:

【Keywords】:

57. 8-Bit Approximations for Parallelism in Deep Learning

【Paper Link】 【Pages】:

【Authors】: Tim Dettmers

【Abstract】:

【Keywords】:

58. Data-dependent initializations of Convolutional Neural Networks

【Paper Link】 【Pages】:

【Authors】: Philipp Kraehenbuehl, Carl Doersch, Jeff Donahue, Trevor Darrell

【Abstract】:

【Keywords】:

59. Order Matters: Sequence to sequence for sets

【Paper Link】 【Pages】:

【Authors】: Oriol Vinyals, Samy Bengio, Manjunath Kudlur

【Abstract】:

【Keywords】:

60. High-Dimensional Continuous Control Using Generalized Advantage Estimation

【Paper Link】 【Pages】:

【Authors】: John Schulman, Philipp Moritz, Sergey Levine, Michael Jordan, Pieter Abbeel

【Abstract】:

【Keywords】:

61. Deep Multi Scale Video Prediction Beyond Mean Square Error

【Paper Link】 【Pages】:

【Authors】: Michael Mathieu, camille couprie, Yann Lecun

【Abstract】:

【Keywords】:

62. Grid Long Short-Term Memory

【Paper Link】 【Pages】:

【Authors】: Nal Kalchbrenner, Alex Graves, Ivo Danihelka

【Abstract】:

【Keywords】:

63. Predicting distributions with Linearizing Belief Networks

【Paper Link】 【Pages】:

【Authors】: Yann Dauphin, David Grangier

【Abstract】:

【Keywords】:

64. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)

【Paper Link】 【Pages】:

【Authors】: Djork-Arné Clevert, Thomas Unterthiner, Sepp Hochreiter

【Abstract】:

【Keywords】:

65. Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning

【Paper Link】 【Pages】:

【Authors】: Emilio Parisotto, Jimmy Ba, Ruslan Salakhutdinov

【Abstract】:

【Keywords】:

66. Segmental Recurrent Neural Networks

【Paper Link】 【Pages】:

【Authors】: Lingpeng Kong, Chris Dyer, Noah Smith

【Abstract】:

【Keywords】:

67. Deep Linear Discriminant Analysis

【Paper Link】 【Pages】:

【Authors】: Matthias Dorfer, Rainer Kelz, Gerhard Widmer

【Abstract】:

【Keywords】:

68. Large-Scale Approximate Kernel Canonical Correlation Analysis

【Paper Link】 【Pages】:

【Authors】: Weiran Wang, Karen Livescu

【Abstract】:

【Keywords】:

69. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

【Paper Link】 【Pages】:

【Authors】: Alec Radford, Luke Metz, Soumith Chintala

【Abstract】:

【Keywords】:

70. Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks

【Paper Link】 【Pages】:

【Authors】: Pouya Bashivan, Irina Rish, Mohammed Yeasin, Noel Codella

【Abstract】:

【Keywords】:

71. Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance

【Paper Link】 【Pages】:

【Authors】: Amr Bakry, Mohamed Elhoseiny, Tarek El-Gaaly, Ahmed Elgammal

【Abstract】:

【Keywords】:

72. An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family

【Paper Link】 【Pages】:

【Authors】: Alexandre De Brébisson, Pascal Vincent

【Abstract】:

【Keywords】:

73. Data-Dependent Path Normalization in Neural Networks

【Paper Link】 【Pages】:

【Authors】: Behnam Neyshabur, Ryota Tomioka, Ruslan Salakhutdinov, Nathan Srebro

【Abstract】:

【Keywords】:

74. Reasoning in Vector Space: An Exploratory Study of Question Answering

【Paper Link】 【Pages】:

【Authors】: Moontae Lee, Xiaodong He, Wen-tau Yih, Jianfeng Gao, Li Deng, Paul Smolensky

【Abstract】:

【Keywords】:

75. Neural GPUs Learn Algorithms

【Paper Link】 【Pages】:

【Authors】: Lukasz Kaiser, Ilya Sutskever

【Abstract】:

【Keywords】:

76. ACDC: A Structured Efficient Linear Layer

【Paper Link】 【Pages】:

【Authors】: Marcin Moczulski, Misha Denil, Jeremy Appleyard, Nando de Freitas

【Abstract】:

【Keywords】:

77. Adversarial Manipulation of Deep Representations

【Paper Link】 【Pages】:

【Authors】: Sara Sabour, Yanshuai Cao, Fartash Faghri, David Fleet

【Abstract】:

【Keywords】:

78. Geodesics of learned representations

【Paper Link】 【Pages】:

【Authors】: Olivier Hénaff, Eero Simoncelli

【Abstract】:

【Keywords】:

79. Sequence Level Training with Recurrent Neural Networks

【Paper Link】 【Pages】:

【Authors】: Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, Wojciech Zaremba

【Abstract】:

【Keywords】:

80. Super-resolution with deep convolutional sufficient statistics

【Paper Link】 【Pages】:

【Authors】: Joan Bruna, Pablo Sprechmann, Yann Lecun

【Abstract】:

【Keywords】: