Thursday, July 13, 2017

Awesome curated list of Paper, Tools, PPTs and Tutorials for Recurrent Neural Networks

Awesome Recurrent Neural Networks

A curated list of resources dedicated to recurrent neural networks (closely related to deep learning). source

Sharing

Table of Contents

Codes

Theory

Lectures

Books / Thesis

Architecture Variants

Structure

  • Bi-directional RNN [Paper]
    • Mike Schuster and Kuldip K. Paliwal, Bidirectional Recurrent Neural Networks, Trans. on Signal Processing 1997
  • Multi-dimensional RNN [Paper]
    • Alex Graves, Santiago Fernandez, and Jurgen Schmidhuber, Multi-Dimensional Recurrent Neural Networks, ICANN 2007
  • GFRNN [Paper-arXiv] [Paper-ICML] [Supplementary]
    • Junyoung Chung, Caglar Gulcehre, Kyunghyun Cho, Yoshua Bengio, Gated Feedback Recurrent Neural Networks, arXiv:1502.02367 / ICML 2015
  • Tree-Structured RNNs
    • Kai Sheng Tai, Richard Socher, and Christopher D. Manning, Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks, arXiv:1503.00075 / ACL 2015 [Paper]
    • Samuel R. Bowman, Christopher D. Manning, and Christopher Potts, Tree-structured composition in neural networks without tree-structured architectures, arXiv:1506.04834 [Paper]
  • Grid LSTM [Paper] [Code]
    • Nal Kalchbrenner, Ivo Danihelka, and Alex Graves, Grid Long Short-Term Memory, arXiv:1507.01526
  • Segmental RNN [Paper]
    • Lingpeng Kong, Chris Dyer, Noah Smith, "Segmental Recurrent Neural Networks", ICLR 2016.
  • Seq2seq for Sets [Paper]
    • Oriol Vinyals, Samy Bengio, Manjunath Kudlur, "Order Matters: Sequence to sequence for sets", ICLR 2016.
  • Hierarchical Recurrent Neural Networks [Paper]
    • Junyoung Chung, Sungjin Ahn, Yoshua Bengio, "Hierarchical Multiscale Recurrent Neural Networks", arXiv:1609.01704

Memory

  • LSTM [Paper]
    • Sepp Hochreiter and Jurgen Schmidhuber, Long Short-Term Memory, Neural Computation 1997
  • GRU (Gated Recurrent Unit) [Paper]
    • Kyunghyun Cho, Bart van Berrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio, Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation, arXiv:1406.1078 / EMNLP 2014
  • NTM [Paper]
    • A.Graves, G. Wayne, and I. Danihelka., Neural Turing Machines, arXiv preprint arXiv:1410.5401
  • Neural GPU [Paper]
    • Łukasz Kaiser, Ilya Sutskever, arXiv:1511.08228 / ICML 2016 (under review)
  • Memory Network [Paper]
    • Jason Weston, Sumit Chopra, Antoine Bordes, Memory Networks, arXiv:1410.3916
  • Pointer Network [Paper]
    • Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly, Pointer Networks, arXiv:1506.03134 / NIPS 2015
  • Deep Attention Recurrent Q-Network [Paper]
    • Ivan Sorokin, Alexey Seleznev, Mikhail Pavlov, Aleksandr Fedorov, Anastasiia Ignateva, Deep Attention Recurrent Q-Network , arXiv:1512.01693
  • Dynamic Memory Networks [Paper]
    • Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, Richard Socher, "Ask Me Anything: Dynamic Memory Networks for Natural Language Processing", arXiv:1506.07285

Surveys

Applications

Natural Language Processing

Language Modeling

  • Tomas Mikolov, Martin Karafiat, Lukas Burget, Jan "Honza" Cernocky, Sanjeev Khudanpur, Recurrent Neural Network based Language Model, Interspeech 2010 [Paper]
  • Tomas Mikolov, Stefan Kombrink, Lukas Burget, Jan "Honza" Cernocky, Sanjeev Khudanpur, Extensions of Recurrent Neural Network Language Model, ICASSP 2011 [Paper]
  • Stefan Kombrink, Tomas Mikolov, Martin Karafiat, Lukas Burget, Recurrent Neural Network based Language Modeling in Meeting Recognition, Interspeech 2011 [Paper]
  • Jiwei Li, Minh-Thang Luong, and Dan Jurafsky, A Hierarchical Neural Autoencoder for Paragraphs and Documents, ACL 2015 [Paper], [Code]
  • Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, and Richard S. Zemel, Skip-Thought Vectors, arXiv:1506.06726 / NIPS 2015 [Paper]
  • Yoon Kim, Yacine Jernite, David Sontag, and Alexander M. Rush, Character-Aware Neural Language Models, arXiv:1508.06615 [Paper]
  • Xingxing Zhang, Liang Lu, and Mirella Lapata, Tree Recurrent Neural Networks with Application to Language Modeling, arXiv:1511.00060 [Paper]
  • Felix Hill, Antoine Bordes, Sumit Chopra, and Jason Weston, The Goldilocks Principle: Reading children's books with explicit memory representations, arXiv:1511.0230 [Paper]

Speech Recognition

  • Geoffrey Hinton, Li Deng, Dong Yu, George E. Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N. Sainath, and Brian Kingsbury, Deep Neural Networks for Acoustic Modeling in Speech Recognition, IEEE Signam Processing Magazine 2012 [Paper]
  • Alex Graves, Abdel-rahman Mohamed, and Geoffrey Hinton, Speech Recognition with Deep Recurrent Neural Networks, arXiv:1303.5778 / ICASSP 2013 [Paper]
  • Jan Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk, Kyunghyun Cho, and Yoshua Bengio, Attention-Based Models for Speech Recognition, arXiv:1506.07503 / NIPS 2015 [Paper]
  • Haşim Sak, Andrew Senior, Kanishka Rao, and Françoise Beaufays. Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition, arXiv:1507.06947 2015 [Paper].

Machine Translation

  • Oxford [Paper]
    • Nal Kalchbrenner and Phil Blunsom, Recurrent Continuous Translation Models, EMNLP 2013
  • Univ. Montreal
    • Kyunghyun Cho, Bart van Berrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio, Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation, arXiv:1406.1078 / EMNLP 2014 [Paper]
    • Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, and Yoshua Bengio, On the Properties of Neural Machine Translation: Encoder-Decoder Approaches, SSST-8 2014 [Paper]
    • Jean Pouget-Abadie, Dzmitry Bahdanau, Bart van Merrienboer, Kyunghyun Cho, and Yoshua Bengio, Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation, SSST-8 2014
    • Dzmitry Bahdanau, KyungHyun Cho, and Yoshua Bengio, Neural Machine Translation by Jointly Learning to Align and Translate, arXiv:1409.0473 / ICLR 2015 [Paper]
    • Sebastian Jean, Kyunghyun Cho, Roland Memisevic, and Yoshua Bengio, On using very large target vocabulary for neural machine translation, arXiv:1412.2007 / ACL 2015 [Paper]
  • Univ. Montreal + Middle East Tech. Univ. + Univ. Maine [Paper]
    • Caglar Gulcehre, Orhan Firat, Kelvin Xu, Kyunghyun Cho, Loic Barrault, Huei-Chi Lin, Fethi Bougares, Holger Schwenk, and Yoshua Bengio, On Using Monolingual Corpora in Neural Machine Translation, arXiv:1503.03535
  • Google [Paper]
    • Ilya Sutskever, Oriol Vinyals, and Quoc V. Le, Sequence to Sequence Learning with Neural Networks, arXiv:1409.3215 / NIPS 2014
  • Google + NYU [Paper]
    • Minh-Thang Luong, Ilya Sutskever, Quoc V. Le, Oriol Vinyals, and Wojciech Zaremba, Addressing the Rare Word Problem in Neural Machine Transltaion, arXiv:1410.8206 / ACL 2015
  • ICT + Huawei [Paper]
    • Fandong Meng, Zhengdong Lu, Zhaopeng Tu, Hang Li, and Qun Liu, A Deep Memory-based Architecture for Sequence-to-Sequence Learning, arXiv:1506.06442
  • Stanford [Paper]
    • Minh-Thang Luong, Hieu Pham, and Christopher D. Manning, Effective Approaches to Attention-based Neural Machine Translation, arXiv:1508.04025
  • Middle East Tech. Univ. + NYU + Univ. Montreal [Paper]
    • Orhan Firat, Kyunghyun Cho, and Yoshua Bengio, Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism, arXiv:1601.01073

Conversation Modeling

  • Lifeng Shang, Zhengdong Lu, and Hang Li, Neural Responding Machine for Short-Text Conversation, arXiv:1503.02364 / ACL 2015 [Paper]
  • Oriol Vinyals and Quoc V. Le, A Neural Conversational Model, arXiv:1506.05869 [Paper]
  • Ryan Lowe, Nissan Pow, Iulian V. Serban, and Joelle Pineau, The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems, arXiv:1506.08909 [Paper]
  • Jesse Dodge, Andreea Gane, Xiang Zhang, Antoine Bordes, Sumit Chopra, Alexander Miller, Arthur Szlam, and Jason Weston, Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems, arXiv:1511.06931 [Paper]
  • Jason Weston, Dialog-based Language Learning, arXiv:1604.06045, [Paper]
  • Antoine Bordes and Jason Weston, Learning End-to-End Goal-Oriented Dialog, arXiv:1605.07683 [Paper]

Question Answering

  • FAIR
    • Jason Weston, Antoine Bordes, Sumit Chopra, Tomas Mikolov, and Alexander M. Rush, Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks, arXiv:1502.05698 [Web] [Paper]
    • Antoine Bordes, Nicolas Usunier, Sumit Chopra, and Jason Weston, Simple Question answering with Memory Networks, arXiv:1506.02075 [Paper]
    • Felix Hill, Antoine Bordes, Sumit Chopra, Jason Weston, "The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations", ICLR 2016 [Paper]
  • DeepMind + Oxford [Paper]
    • Karl M. Hermann, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom, Teaching Machines to Read and Comprehend, arXiv:1506.03340 / NIPS 2015
  • MetaMind [Paper]
    • Ankit Kumar, Ozan Irsoy, Jonathan Su, James Bradbury, Robert English, Brian Pierce, Peter Ondruska, Mohit Iyyer, Ishaan Gulrajani, and Richard Socher, Ask Me Anything: Dynamic Memory Networks for Natural Language Processing, arXiv:1506.07285

Computer Vision

Object Recognition

  • Pedro Pinheiro and Ronan Collobert, Recurrent Convolutional Neural Networks for Scene Labeling, ICML 2014 [Paper]
  • Ming Liang and Xiaolin Hu, Recurrent Convolutional Neural Network for Object Recognition, CVPR 2015 [Paper]
  • Wonmin Byeon, Thomas Breuel, Federico Raue1, and Marcus Liwicki1, Scene Labeling with LSTM Recurrent Neural Networks, CVPR 2015 [Paper]
  • Mircea Serban Pavel, Hannes Schulz, and Sven Behnke, Recurrent Convolutional Neural Networks for Object-Class Segmentation of RGB-D Video, IJCNN 2015 [Paper]
  • Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes, Vibhav Vineet, Zhizhong Su, Dalong Du, Chang Huang, and Philip H. S. Torr, Conditional Random Fields as Recurrent Neural Networks, arXiv:1502.03240 [Paper]
  • Xiaodan Liang, Xiaohui Shen, Donglai Xiang, Jiashi Feng, Liang Lin, and Shuicheng Yan, Semantic Object Parsing with Local-Global Long Short-Term Memory, arXiv:1511.04510 [Paper]
  • Sean Bell, C. Lawrence Zitnick, Kavita Bala, and Ross Girshick, Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks, arXiv:1512.04143 / ICCV 2015 workshop [Paper]

Visual Tracking

  • Quan Gan, Qipeng Guo, Zheng Zhang, and Kyunghyun Cho, First Step toward Model-Free, Anonymous Object Tracking with Recurrent Neural Networks, arXiv:1511.06425 [Paper]

Image Generation

  • Karol Gregor, Ivo Danihelka, Alex Graves, Danilo J. Rezende, and Daan Wierstra, DRAW: A Recurrent Neural Network for Image Generation, ICML 2015 [Paper]
  • Angeliki Lazaridou, Dat T. Nguyen, R. Bernardi, and M. Baroni, Unveiling the Dreams of Word Embeddings: Towards Language-Driven Image Generation, arXiv:1506.03500 [Paper]
  • Lucas Theis and Matthias Bethge, Generative Image Modeling Using Spatial LSTMs, arXiv:1506.03478 / NIPS 2015 [Paper]
  • Aaron van den Oord, Nal Kalchbrenner, and Koray Kavukcuoglu, Pixel Recurrent Neural Networks, arXiv:1601.06759 [Paper]

Video Analysis

  • Univ. Toronto [paper]
    • Nitish Srivastava, Elman Mansimov, Ruslan Salakhutdinov, Unsupervised Learning of Video Representations using LSTMs, arXiv:1502.04681 / ICML 2015
  • Univ. Cambridge [paper]
    • Viorica Patraucean, Ankur Handa, Roberto Cipolla, Spatio-temporal video autoencoder with differentiable memory, arXiv:1511.06309

Multimodal (CV + NLP)

Image Captioning

  • UCLA + Baidu [Web] [Paper-arXiv1], [Paper-arXiv2]
    • Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, and Alan L. Yuille, Explain Images with Multimodal Recurrent Neural Networks, arXiv:1410.1090
    • Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, Zhiheng Huang, and Alan L. Yuille, Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN), arXiv:1412.6632 / ICLR 2015
  • Univ. Toronto [Paper] [Web demo]
    • Ryan Kiros, Ruslan Salakhutdinov, and Richard S. Zemel, Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models, arXiv:1411.2539 / TACL 2015
  • Berkeley [Web] [Paper]
    • Jeff Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, and Trevor Darrell, Long-term Recurrent Convolutional Networks for Visual Recognition and Description, arXiv:1411.4389 / CVPR 2015
  • Google [Paper]
    • Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan, Show and Tell: A Neural Image Caption Generator, arXiv:1411.4555 / CVPR 2015
  • Stanford [Web] [Paper]
    • Andrej Karpathy and Li Fei-Fei, Deep Visual-Semantic Alignments for Generating Image Description, CVPR 2015
  • Microsoft [Paper]
    • Hao Fang, Saurabh Gupta, Forrest Iandola, Rupesh Srivastava, Li Deng, Piotr Dollar, Jianfeng Gao, Xiaodong He, Margaret Mitchell, John C. Platt, Lawrence Zitnick, and Geoffrey Zweig, From Captions to Visual Concepts and Back, arXiv:1411.4952 / CVPR 2015
  • CMU + Microsoft [Paper-arXiv], [Paper-CVPR]
    • Xinlei Chen, and C. Lawrence Zitnick, Learning a Recurrent Visual Representation for Image Caption Generation
    • Xinlei Chen, and C. Lawrence Zitnick, Mind’s Eye: A Recurrent Visual Representation for Image Caption Generation, CVPR 2015
  • Univ. Montreal + Univ. Toronto [Web] [Paper]
    • Kelvin Xu, Jimmy Lei Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard S. Zemel, and Yoshua Bengio, Show, Attend, and Tell: Neural Image Caption Generation with Visual Attention, arXiv:1502.03044 / ICML 2015
  • Idiap + EPFL + Facebook [Paper]
    • Remi Lebret, Pedro O. Pinheiro, and Ronan Collobert, Phrase-based Image Captioning, arXiv:1502.03671 / ICML 2015
  • UCLA + Baidu [Paper]
    • Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, Zhiheng Huang, and Alan L. Yuille, Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images, arXiv:1504.06692
  • MS + Berkeley
    • Jacob Devlin, Saurabh Gupta, Ross Girshick, Margaret Mitchell, and C. Lawrence Zitnick, Exploring Nearest Neighbor Approaches for Image Captioning, arXiv:1505.04467 (Note: technically not RNN) [Paper]
    • Jacob Devlin, Hao Cheng, Hao Fang, Saurabh Gupta, Li Deng, Xiaodong He, Geoffrey Zweig, and Margaret Mitchell, Language Models for Image Captioning: The Quirks and What Works, arXiv:1505.01809 [Paper]
  • Adelaide [Paper]
    • Qi Wu, Chunhua Shen, Anton van den Hengel, Lingqiao Liu, and Anthony Dick, Image Captioning with an Intermediate Attributes Layer, arXiv:1506.01144
  • Tilburg [Paper]
    • Grzegorz Chrupala, Akos Kadar, and Afra Alishahi, Learning language through pictures, arXiv:1506.03694
  • Univ. Montreal [Paper]
    • Kyunghyun Cho, Aaron Courville, and Yoshua Bengio, Describing Multimedia Content using Attention-based Encoder-Decoder Networks, arXiv:1507.01053
  • Cornell [Paper]
    • Jack Hessel, Nicolas Savva, and Michael J. Wilber, Image Representations and New Domains in Neural Image Captioning, arXiv:1508.02091

Video Captioning

  • Berkeley [Web] [Paper]
    • Jeff Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, and Trevor Darrell, Long-term Recurrent Convolutional Networks for Visual Recognition and Description, arXiv:1411.4389 / CVPR 2015
  • UT Austin + UML + Berkeley [Paper]
    • Subhashini Venugopalan, Huijuan Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, and Kate Saenko, Translating Videos to Natural Language Using Deep Recurrent Neural Networks, arXiv:1412.4729
  • Microsoft [Paper]
    • Yingwei Pan, Tao Mei, Ting Yao, Houqiang Li, and Yong Rui, Joint Modeling Embedding and Translation to Bridge Video and Language, arXiv:1505.01861
  • UT Austin + Berkeley + UML [Paper]
    • Subhashini Venugopalan, Marcus Rohrbach, Jeff Donahue, Raymond Mooney, Trevor Darrell, and Kate Saenko, Sequence to Sequence--Video to Text, arXiv:1505.00487
  • Univ. Montreal + Univ. Sherbrooke [Paper]
    • Li Yao, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo Larochelle, and Aaron Courville, Describing Videos by Exploiting Temporal Structure, arXiv:1502.08029
  • MPI + Berkeley [Paper]
    • Anna Rohrbach, Marcus Rohrbach, and Bernt Schiele, The Long-Short Story of Movie Description, arXiv:1506.01698
  • Univ. Toronto + MIT [Paper]
    • Yukun Zhu, Ryan Kiros, Richard Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, and Sanja Fidler, Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books, arXiv:1506.06724
  • Univ. Montreal [Paper]
    • Kyunghyun Cho, Aaron Courville, and Yoshua Bengio, Describing Multimedia Content using Attention-based Encoder-Decoder Networks, arXiv:1507.01053
  • Zhejiang Univ. + UTS [Paper]
    • Pingbo Pan, Zhongwen Xu, Yi Yang, Fei Wu, Yueting Zhuang, Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning, arXiv:1511.03476
  • Univ. Montreal + NYU + IBM [Paper]
    • Li Yao, Nicolas Ballas, Kyunghyun Cho, John R. Smith, and Yoshua Bengio, Empirical performance upper bounds for image and video captioning, arXiv:1511.04590

Visual Question Answering

  • Virginia Tech. + MSR [Web] [Paper]
    • Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C. Lawrence Zitnick, and Devi Parikh, VQA: Visual Question Answering, arXiv:1505.00468 / CVPR 2015 SUNw:Scene Understanding workshop
  • MPI + Berkeley [Web] [Paper]
    • Mateusz Malinowski, Marcus Rohrbach, and Mario Fritz, Ask Your Neurons: A Neural-based Approach to Answering Questions about Images, arXiv:1505.01121
  • Univ. Toronto [Paper] [Dataset]
    • Mengye Ren, Ryan Kiros, and Richard Zemel, Exploring Models and Data for Image Question Answering, arXiv:1505.02074 / ICML 2015 deep learning workshop
  • Baidu + UCLA [Paper] [Dataset]
    • Hauyuan Gao, Junhua Mao, Jie Zhou, Zhiheng Huang, Lei Wang, and Wei Xu, Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering, arXiv:1505.05612 / NIPS 2015
  • SNU + NAVER [Paper]
    • Jin-Hwa Kim, Sang-Woo Lee, Dong-Hyun Kwak, Min-Oh Heo, Jeonghee Kim, Jung-Woo Ha, Byoung-Tak Zhang, Multimodal Residual Learning for Visual QA, arXiv:1606:01455
  • UC Berkeley + Sony [Paper]
    • Akira Fukui, Dong Huk Park, Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach, Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding, arXiv:1606.01847
  • Postech [Paper]
    • Hyeonwoo Noh and Bohyung Han, Training Recurrent Answering Units with Joint Loss Minimization for VQA, arXiv:1606.03647
  • SNU + NAVER [Paper]
    • Jin-Hwa Kim, Kyoung Woon On, Jeonghee Kim, Jung-Woo Ha, Byoung-Tak Zhang, Hadamard Product for Low-rank Bilinear Pooling, arXiv:1610.04325
  • Video QA
    • CMU + UTS [paper]
      • Linchao Zhu, Zhongwen Xu, Yi Yang, Alexander G. Hauptmann, Uncovering Temporal Context for Video Question and Answering, arXiv:1511.04670
    • KIT + MIT + Univ. Toronto [Paper] [Dataset]
      • Makarand Tapaswi, Yukun Zhu, Rainer Stiefelhagen, Antonio Torralba, Raquel Urtasun, Sanja Fidler, MovieQA: Understanding Stories in Movies through Question-Answering, arXiv:1512.02902

Turing Machines

  • A.Graves, G. Wayne, and I. Danihelka., Neural Turing Machines, arXiv preprint arXiv:1410.5401 [Paper]
  • Jason Weston, Sumit Chopra, Antoine Bordes, Memory Networks, arXiv:1410.3916 [Paper]
  • Armand Joulin and Tomas Mikolov, Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets, arXiv:1503.01007 / NIPS 2015 [Paper]
  • Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, and Rob Fergus, End-To-End Memory Networks, arXiv:1503.08895 / NIPS 2015 [Paper]
  • Wojciech Zaremba and Ilya Sutskever, Reinforcement Learning Neural Turing Machines, arXiv:1505.00521 [Paper]
  • Baolin Peng and Kaisheng Yao, Recurrent Neural Networks with External Memory for Language Understanding, arXiv:1506.00195 [Paper]
  • Fandong Meng, Zhengdong Lu, Zhaopeng Tu, Hang Li, and Qun Liu, A Deep Memory-based Architecture for Sequence-to-Sequence Learning, arXiv:1506.06442 [Paper]
  • Arvind Neelakantan, Quoc V. Le, and Ilya Sutskever, Neural Programmer: Inducing Latent Programs with Gradient Descent, arXiv:1511.04834 [Paper]
  • Scott Reed and Nando de Freitas, Neural Programmer-Interpreters, arXiv:1511.06279 [Paper]
  • Karol Kurach, Marcin Andrychowicz, and Ilya Sutskever, Neural Random-Access Machines, arXiv:1511.06392 [Paper]
  • Łukasz Kaiser and Ilya Sutskever, Neural GPUs Learn Algorithms, arXiv:1511.08228 [Paper]
  • Ethan Caballero, Skip-Thought Memory Networks, arXiv:1511.6420 [Paper]
  • Wojciech Zaremba, Tomas Mikolov, Armand Joulin, and Rob Fergus, Learning Simple Algorithms from Examples, arXiv:1511.07275 [Paper]

Robotics

  • Hongyuan Mei, Mohit Bansal, and Matthew R. Walter, Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences, arXiv:1506.04089 [Paper]
  • Marvin Zhang, Sergey Levine, Zoe McCarthy, Chelsea Finn, and Pieter Abbeel, Policy Learning with Continuous Memory States for Partially Observed Robotic Control, arXiv:1507.01273. [Paper]

Other

  • Alex Graves, Generating Sequences With Recurrent Neural Networks, arXiv:1308.0850 [Paper]
  • Volodymyr Mnih, Nicolas Heess, Alex Graves, and Koray Kavukcuoglu, Recurrent Models of Visual Attention, NIPS 2014 / arXiv:1406.6247 [Paper]
  • Wojciech Zaremba and Ilya Sutskever, Learning to Execute, arXiv:1410.4615 [Paper] [Code]
  • Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer, Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks, arXiv:1506.03099 / NIPS 2015 [Paper]
  • Bing Shuai, Zhen Zuo, Gang Wang, and Bing Wang, DAG-Recurrent Neural Networks For Scene Labeling, arXiv:1509.00552 [Paper]
  • Soren Kaae Sonderby, Casper Kaae Sonderby, Lars Maaloe, and Ole Winther, Recurrent Spatial Transformer Networks, arXiv:1509.05329 [Paper]
  • Cesar Laurent, Gabriel Pereyra, Philemon Brakel, Ying Zhang, and Yoshua Bengio, Batch Normalized Recurrent Neural Networks, arXiv:1510.01378 [Paper]
  • Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee, Deeply-Recursive Convolutional Network for Image Super-Resolution, arXiv:1511.04491 [Paper]
  • Quan Gan, Qipeng Guo, Zheng Zhang, and Kyunghyun Cho, First Step toward Model-Free, Anonymous Object Tracking with Recurrent Neural Networks, arXiv:1511.06425 [Paper]
  • Francesco Visin, Kyle Kastner, Aaron Courville, Yoshua Bengio, Matteo Matteucci, and Kyunghyun Cho, ReSeg: A Recurrent Neural Network for Object Segmentation, arXiv:1511.07053 [Paper]
  • Juergen Schmidhuber, On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models, arXiv:1511.09249 [Paper]

Datasets

Blogs

Online Demos

  • Alex graves, hand-writing generation [link]
  • Ink Poster: Handwritten post-it notes [link]
  • LSTMVis: Visual Analysis for Recurrent Neural Networks [link]

Thursday, February 11, 2016

Top 11 PHP Frameworks for Web Developer: A Review

PHP, known as the most popular server-side scripting language in the world, has evolved a lot since the first inline code snippets appeared in static HTML files.
These days developers need to build complex websites and web apps, and above a certain complexity level it can take too much time and hassle to always start from scratch, hence came the need for a more structured natural way of development. PHP frameworks provide developers with an adequate solution for that.
In this post we carefully handpicked 10 popular PHP frameworks that can bestfacilitate and streamline the process of backend web development.

Why Use A PHP Framework

But first, let’s take a look at the top reasons why many developers like to use PHP frameworks and how these frameworks can level up your development process. Here’s what PHP frameworks do:
  • Make speed development possible
  • Provide well-organized, reusable and maintainable code
  • Let you grow over time as web apps running on frameworks are scalable
  • Spare you from the worries about low-level security of a site
  • Follow the MVC (Model-View-Controller) pattern that ensures the separation of presentation and logic
  • Promote modern web development practices such as object-oriented programming tools

1. Laravel

Although Laravel is a relatively new PHP framework (it was released in 2011), according to Sitepoint’s recent online survey it is the most popular framework among developers. Laravel has a huge ecosystem with an instant hosting and deployment platform, and its official website offers many screencast tutorials called Laracasts.
Laravel has many features that make rapid application development possible. Laravel has its own light-weight templating engine called “Blade”, elegant syntax that facilitates tasks you frequently need to do, such as authentication, sessions, queueing, caching and RESTful routing. Laravel also includes a local development environment called Homestead that is a packaged Vagrant box.


Laravel

2. Symfony

The components of the Symfony 2 framework are used by many impressive projects such as the Drupal content management system, or the phpBB forum software, but Laravel – the framework listed above – also relies on it. Symfony has a wide developer community and many ardent fans.
Symfony Components are reusable PHP libraries that you can complete different tasks with, such as form creation, object configuration, routing, authentication, templating, and many others. You can install any of the Components with the Composer PHP dependency manager. The website of Symfony has a cool showcase section where you can take a peek at the projects developers accomplished with the help of this handy framework.


Symfony

3. CodeIgniter

CodeIgniter is a lightweight PHP framework that is almost 10 years old (initially released in 2006). CodeIgniter has a very straightforward installation process that requires only a minimal configuration, so it can save you a lot of hassle. It’s also an ideal choice if you want to avoid PHP version conflict, as it works nicely on almost all shared and dedicated hosting platforms (currently requires only PHP 5.2.4).
CodeIgniter is not strictly based on the MVC development pattern. Using Controller classes is a must, but Models and Views are optional, and you can use your own coding and naming conventions, evidence that CodeIgniter gives great freedom to developers. If you download it, you’ll see it’s only about 2MB, so it’s a lean framework, but it allows you to add third-party plugins if you need more complicated functionalities.


CodeIgniter

4. Yii 2

If you choose the Yii framework you give a boost to the performance of your site as it’s faster than other PHP frameworks, because it extensively uses the lazy loading technique. Yii 2 is purely object-oriented, and it’s based on theDRY (Don’t Repeat Yourself) coding concept, so it provides you with a pretty clean and logical code base.
Yii 2 is integrated with jQuery, and it comes with a set of AJAX-enabled features, and it implements an easy-to-use skinning and theming mechanism, so it can be a great choice for someone who comes from a frontend background. It has also a powerful class code generator called Gii that facilitates object-oriented programming and rapid prototyping, and provides a web-based interface that allows you to interactively generate the code you need.


Yii

5. Phalcon

The Phalcon framework was released in 2012, and it quickly gained popularity among PHP developers. Phalcon is said to be fast as a falcon, because it waswritten in C and C++ to reach the highest level of performance optimization possible. Good news is that you don’t have to learn the C language, as the functionality is exposed as PHP classes that are ready to use for any application.
As Phalcon is delivered as a C-extension, its architecture is optimized at low levels which significantly reduces the overhead typical of MVC-based apps. Phalcon not only boosts execution speeds, but also decreases resource usage. Phalcon is also packed with many cool features such as a universal auto-loader, asset management, security, translation, caching, and many others. As it’s awell-documented and easy-to-use framework, it’s definitely worth a try.


Phalcon


6. Nette PHP

Nette Framework is an open-source framework for creating web applications in PHP 5. It supports AJAX, DRY, KISS, MVC and code reusability. Original author of the framework is David Grudl, but further development is now maintained by the Nette Foundation organization. Nette is a free software released under both the New BSD license and the GNU GPL version 2 or 3.




7. CakePHP

CakePHP is already a decade old (the first version was released in 2005), but it’s still among the most popular PHP frameworks, as it has always managed to keep up with time. The latest version, CakePHP 3.0 enhanced session management,improved modularity by decoupling several components, and increased the ability of creating more standalone libraries.
CakePHP has a really remarkable showcase, it powers the websites of big brands such as BMWHyundai, and Express. It is an excellent tool for creating web apps that need high-level of security, as it has many built-in security features such as input validation, SQL injection prevention, XSS (cross-site scripting) prevention, CSRF (cross-site request forgery) protection, and many others.


CakePHP

8. Zend Framework

Zend is a robust and stable PHP framework packed with a lot of configuration options therefore it’s usually not recommended for smaller projects butexcellent for more complex ones. Zend has partners such as IBM, Microsoft, Google and Adobe. The coming major release, Zend Framework 3 will beoptimized for PHP 7 , but will still support PHP 5.5 onwards.
The current release, Zend Framework 2 also has many cool features such as cryptographic coding tools, an easy-to-use drag and drop editor with support for front-end technologies (HTML, CSS, JavaScript), instant online debugging and PHP Unit testing tools, and a connected Database Wizard. Zend Framework was created with the Agile methodology that facilitates delivering high-quality apps to enterprise clients.


Zend Framework

9. Slim

Slim is a PHP micro framework that provides you with everything you need and nothing you don’t. Micro frameworks are minimalistic in design, they areexcellent for smaller apps where a full-stack framework would be an exaggeration. Slim’s creator was inspired by a Ruby micro framework calledSinatra.
Slim is used by many PHP developers for developing RESTful APIs and services. Slim comes with features such as URL routing, client-side HTTP caching, session- and cookie encryption, and it supports “flash” messages across HTTP requests as well. Its User Guide is an easy read, and if you are interested in the new features of the upcoming major release (already in beta), you can watch this primer video about Slim 3.


Slim

10. FuelPHP

FuelPHP is a flexible full-stack PHP framework that doesn’t only support the ordinary MVC pattern but also its evolved version, HMVC (Hierarchical Model-View-Controller) at the architecture level. FuelPHP adds an optional classcalled Presenter (formerly called ViewModel) between the Controller and View layers to hold the logic needed to generate Views.
FuelPHP is modular and extendable, takes care of security concerns by providing features such as input and URI filtering and output encoding, and it comes with its own authentication framework, with many other sophisticatedfeatures and a detailed documentation.


FuelPHP

11. PHPixie

PHPixie is a quite new framework, it started in 2012 with the goal of creating a high-performance framework for read-only websites. PHPixie also implements the HMVC design pattern just like FuelPHP, and is built by using independentcomponents that can be used as well without the framework itself. The PHPixie components are 100% unit tested, and require minimum dependencies.
The official website has a tutorial that claims you can learn the framework in 30 minutes, and their blog also details many practical use cases. Among the features you can find the standard ORM (object-relational mapping), caching, input validation, authentication and authorization capabilities. PHPixie also allows you to use the HAML markup language, enables schema migration, and has a sophisticated routing system.


PHPixie