2015.md

2015

Deep learning

• [ADAM] Adam: A Method for Stochastic Optimization. [[pdf]](docs/2015/ADAM- A METHOD FOR STOCHASTIC OPTIMIZATION(2015).pdf) [url] ⭐
• A Diversity-Promoting Objective Function for Neural Conversation Models. [[pdf](docs/2015/A Diversity-Promoting Objective Function for Neural Conversation Models.pdf)] [url]
• A Neural Conversational Model. [[pdf]](docs/2015/A Neural Conversational Model.pdf) [url]
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses. [[pdf]](docs/2015/A Neural Network Approach to Context-Sensitive Generation of Conversational Responses.pdf) [url]
• A Roadmap towards Machine Intelligence. [url]
• A Survey- Time Travel in Deep Learning Space- An Introduction to Deep Learning Models and How Deep Learning Models Evolved from the Initial Ideas. [[pdf]](docs/2015/A Survey- Time Travel in Deep Learning Space- An Introduction to Deep Learning Models and How Deep Learning Models Evolved from the Initial Ideas.pdf) [url]
• An Empirical Exploration of Recurrent Network Architectures. [[pdf]](docs/2015/An Empirical Exploration of Recurrent Network Architectures(2015).pdf) [url] ⭐
• [Batch Normalization] Batch Normalization- Accelerating Deep Network Training by Reducing Internal Covariate Shift. [arxiv] ⭐
• Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models. [url]
• Correlational Neural Networks. [url]
• Deconstructing the Ladder Network Architecture. [url]
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. [arxiv]
• Deep Knowledge Tracing. [url]
• Deep learning. [nature] ⭐
• Distilling the Knowledge in a Neural Network. [[pdf]](docs/2015/Distilling the Knowledge in a Neural Network.pdf) [url] ⭐
• Dropout as a Bayesian Approximation- Representing Model Uncertainty in Deep Learning. [url]
• Effective LSTMs for Target-Dependent Sentiment Classification. [arxiv]
• Human-level concept learning through probabilistic program induction [science] ⭐
• Learning Simple Algorithms from Examples. [[pdf]](docs/2015/Learning Simple Algorithms from Examples.pdf) [url]
• Learning to Transduce with Unbounded Memory. [url]
• LSTM A Search Space Odyssey. [[pdf]](docs/2015/LSTM A Search Space Odyssey(2015).pdf) [url] ⭐
• LSTM-based Deep Learning Models for non-factoid answer selection. [url]
• Neural GPUs Learn Algorithms. [[pdf]](docs/2015/Neural GPUs Learn Algorithms.pdf) [arxiv] [tensorflow] ⭐
• Neural Programmer- Inducing Latent Programs with Gradient Descent. [url]
• Pointer Networks. [arxiv] [tensorflow] ⭐
• Poker-CNN- A Pattern Learning Strategy for Making Draws and Bets in Poker Games. [[pdf]](docs/2015/Poker-CNN- A Pattern Learning Strategy for Making Draws and Bets in Poker Games.pdf) [url]
• Policy distillation. [arxiv] ⭐
• Regularizing RNNs by Stabilizing Activations. [url]
• ReNet- A Recurrent Neural Network Based Alternative to Convolutional Networks. [[pdf]](docs/2015/ReNet- A Recurrent Neural Network Based Alternative to Convolutional Networks.pdf) [url]
• Semi-Supervised Learning with Ladder Networks. [url] ⭐
• Session-based Recommendations with Recurrent Neural Networks. [url]
• Skip-Thought Vectors. [[pdf]](docs/2015/Skip-Thought Vectors.pdf) [url] ⭐
• Training Very Deep Networks. [[pdf]](docs/2015/Training Very Deep Networks.pdf) [url] ⭐
• Tree-structured composition in neural networks without tree-structured architectures. [[pdf]](docs/2015/Tree-structured composition in neural networks without tree-structured architectures.pdf) [url]

Computer vision

• A Neural Algorithm of Artistic Style. [arxiv] [code] ⭐
• [ResNet] Deep Residual Learning for Image Recognition. [[pdf]](docs/2015/Deep Residual Learning for Image Recognition.pdf) [arxiv] [tensorflow] ⭐
• [ResNet] Delving Deep into Rectifiers- Surpassing Human-Level Performance on ImageNet Classification. [[pdf]](docs/2015/Delving Deep into Rectifiers- Surpassing Human-Level Performance on ImageNet Classification(2015).pdf) [url] ⭐
• [FaceNet] FaceNet: A Unified Embedding for Face Recognition and Clustering. [arxiv] [tensorflow] ⭐
• [Faster R-CNN] Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. [arxiv] [code] ⭐
• [Fast R-CNN] Fast R-CNN [arxiv] [code] ⭐
• Hierarchical Recurrent Neural Network for Skeleton Based Action Recognition. [url] ⭐
• Inceptionism: Going Deeper into Neural Networks. [googleblog] ⭐
• Inside-Outside Net- Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks. [[pdf]](docs/2015/Inside-Outside Net- Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks.pdf) [url]
• ReSeg- A Recurrent Neural Network for Object Segmentation. [[pdf]](docs/2015/ReSeg- A Recurrent Neural Network for Object Segmentation.pdf) [url] ⭐
• Rethinking the Inception Architecture for Computer Vision. [[pdf]](docs/2015/Rethinking the Inception Architecture for Computer Vision.pdf) [arxiv] [tensorflow] ⭐
• [FCNT] Visual Tracking with fully Convolutional Networks. [cuhk] [code] ⭐
• You Only Look Once: Unified, Real-Time Object Detection. [arxiv]

Generative learning

• Adversarial Autoencoders. [arxiv]
• A note on the evaluation of generative models. [arxiv] ⭐
• Autoencoding beyond pixels using a learned similarity metric. [arxiv] ⭐
• Censoring Representations with an Adversary. [arxiv]
• Conditional generative adversarial nets for convolutional face generation. [pdf]
• [LAPGAN] Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks [arxiv] [code] ⭐
• Distributional Smoothing with Virtual Adversarial Training. [arxiv] ⭐
• [VAE with attention] DRAW: A Recurrent Neural Network For Image Generation. [arxiv] [code] ⭐
• Exploring the Space of Adversarial Images. [arxiv] [code] ⭐
• Generative Adversarial Networks in Estimation of Distribution Algorithms for Combinatorial Optimization. [arxiv] [code]
• Generative Image Modeling Using Spatial LSTMs. [arxiv]
• Generative Moment Matching Networks. [arxiv] ⭐
• Improving Semi-Supervised Learning with Auxiliary Deep Generative Models. [pdf]
• [CVAE] Learning Structured Output Representation using Deep Conditional Generative Models. [] ⭐
• Max-margin Deep Generative Models. [arxiv] [code]
• Semi-Supervised Learning with Ladder Networks. [arxiv] ⭐
• [CatGAN] Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks. [arxiv] ⭐
• [DCGAN] Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. [arxiv] [tensorflow] ⭐

Attention and memory

• [ABCNN] ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs. [arxiv] ⭐
• Action Recognition using Visual Attention. [arxiv] [code]
• Ask Me Anything- Dynamic Memory Networks for Natural Language Processing. [url] ⭐
• Attention-Based Models for Speech Recognition. [arxiv]
• Attention with Intention for a Neural Network Conversation Model. [url]
• [VAE with attention] DRAW: A Recurrent Neural Network For Image Generation. [arxiv] [code] ⭐
• Show, Attend and Tell- Neural Image Caption Generation with Visual Attention. [url] ⭐
• Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation. [arxiv]
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing. [arxiv] ⭐
• A Neural Attention Model for Sentence Summarization. [url] ⭐
• [Global And Local Attention] Effective Approaches to Attention-based Neural Machine Translation. [arxiv] [code] [tensorflow] ⭐
• End-to-End Attention-based Large Vocabulary Speech Recognition. [url]
• End-To-End Memory Networks. [arxiv] ⭐
• Grammar as a Foreign Language. [arxiv] ⭐
• Large-scale Simple Question Answering with Memory Networks. [arxiv]
• Learning Deep Neural Network Policies with Continuous Memory States. [arxiv]
• [LAS] Listen, Attend and Spell. [[pdf]](docs/2015/Listen, Attend and Spell.pdf) [arxiv] ⭐
• Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences. [arxiv] ⭐
• Memory-based control with recurrent neural networks. [arxiv]
• Not All Contexts Are Created Equal: Better Word Representations with Variable Attention. [pdf]
• Reinforcement Learning Neural Turing Machines. [arxiv] ⭐
• [Soft And Hard Attention] Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. [arxiv] [code] [tensorflow] ⭐
• Teaching Machines to Read and Comprehend. [arxiv] ⭐
• Video Description Generation Incorporating Spatio-Temporal Features and a Soft-Attention Mechanism. [arxiv]

Transfer learning

• Heterogeneous defect prediction. [pdf]
• Learning Transferred Weights From Co-Occurrence Data for Heterogeneous Transfer Learning. [pdf]
• Net2Net-Accelerating Learning via Knowledge Transfer. [arxiv] ⭐
• Spatial Transformer Networks. [arxiv] [tensorflow] ⭐
• Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping. [arxiv]
• Transfer learning using computational intelligence: A survey. [url]
• Transfer learning used to analyze the dynamic evolution of the dust aerosol. [url]
• Transferring Rich Feature Hierarchies for Robust Visual Tracking. [arxiv] ⭐

One/zero-shot learning

• Siamese Neural Networks for One-shot Image Recognition. [pdf]

Deep reinforcement learning

• ADAAPT: A Deep Architecture for Adaptive Policy Transfer from Multiple Sources. [arxiv]
• Action-Conditional Video Prediction using Deep Networks in Atari Games. [arxiv] ⭐
• Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning. [arxiv] ⭐
• [DDPG] Continuous control with deep reinforcement learning. [arxiv] ⭐
• [NAF] Continuous Deep Q-Learning with Model-based Acceleration. [arxiv] ⭐
• Dueling Network Architectures for Deep Reinforcement Learning. [arxiv] ⭐
• Deep Reinforcement Learning with an Action Space Defined by Natural Language. [arxiv]
• Deep Reinforcement Learning with Double Q-learning. [arxiv] ⭐
• Deep Recurrent Q-Learning for Partially Observable MDPs. [arxiv] ⭐
• DeepMPC: Learning Deep Latent Features for Model Predictive Control. [url]
• Deterministic Policy Gradient Algorithms. [url] ⭐
• Dueling Network Architectures for Deep Reinforcement Learning. [arxiv]
• End-to-End Training of Deep Visuomotor Policies. [arxiv] ⭐
• Giraffe: Using Deep Reinforcement Learning to Play Chess. [arxiv]
• Generating Text with Deep Reinforcement Learning. [arxiv]
• How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies. [arxiv]
• Human-level control through deep reinforcement learning. [nature] ⭐
• Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models. [arxiv] ⭐
• Learning Simple Algorithms from Examples. [arxiv]
• Language Understanding for Text-based Games Using Deep Reinforcement Learning. [url] ⭐
• Learning Continuous Control Policies by Stochastic Value Gradients. [url] ⭐
• Multiagent Cooperation and Competition with Deep Reinforcement Learning. [arxiv]
• Maximum Entropy Deep Inverse Reinforcement Learning. [arxiv]
• Massively Parallel Methods for Deep Reinforcement Learning. [url] ⭐
• On Learning to Think- Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models. [arxiv]
• Playing Atari with Deep Reinforcement Learning. [arxiv]
• Recurrent Reinforcement Learning: A Hybrid Approach. [arxiv]
• Strategic Dialogue Management via Deep Reinforcement Learning. [arxiv]
• Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control. [arxiv]
• Trust Region Policy Optimization. [url] ⭐
• Universal Value Function Approximators. [url]
• Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning. [arxiv]

Natural language process

• A Primer on Neural Network Models for Natural Language Processing. [url]
• A Unified Tagging Solution- Bidirectional LSTM Recurrent Neural Network with Word Embedding. [url]
• Alternative structures for character-level RNNs. [[pdf]](docs/2015/Alternative structures for character-level RNNs.pdf) [url]
• Ask Me Anything- Dynamic Memory Networks for Natural Language Processing. [url] ⭐
• BlackOut- Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies. [url]
• Character-Aware Neural Language Models. [url] ⭐
• Character-level Convolutional Networks for Text Classification. [[pdf]](docs/2015/Character-level Convolutional Networks for Text Classification.pdf) [url]
• Deep Speech 2- End-to-End Speech Recognition in English and Mandarin. [[pdf]](docs/2015/Deep Speech 2- End-to-End Speech Recognition in English and Mandarin.pdf) [url] ⭐
• Distributed Representations of Sentences and Documents. [[pdf]](docs/2015/Distributed Representations of Sentences and Documents.pdf) [url] ⭐
• Dynamic Capacity Networks. [[pdf]](docs/2015/Dynamic Capacity Networks.pdf) [url]
• Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs. [[pdf]](docs/2015/Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs.pdf) [url]
• Larger-Context Language Modeling. [[pdf]](docs/2015/Larger-Context Language Modeling.pdf) [url]
• Multi-task Sequence to Sequence Learning. [[pdf]](docs/2015/Multi-task Sequence to Sequence Learning.pdf) [url]
• Natural Language Understanding with Distributed Representation. [[pdf]](docs/2015/Natural Language Understanding with Distributed Representation.pdf) [url]
• Neural Machine Translation of Rare Words with Subword Units. [arxiv]
• Neural Responding Machine for Short-Text Conversation. [url]
• Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network. [[pdf]](docs/2015/Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network.pdf) [url]
• Reading Scene Text in Deep Convolutional Sequences. [url]
• Recurrent Convolutional Neural Networks for Text Classification. [pdf]
• Semi-supervised Sequence Learning. [[pdf]](docs/2015/Semi-supervised Sequence Learning.pdf) [url]
• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems. [arxiv]
• sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In Neural Word Embeddings. [url]
• Sequence Level Training with Recurrent Neural Networks. [[pdf]](docs/2015/Sequence Level Training with Recurrent Neural Networks.pdf) [url]
• Strategies for Training Large Vocabulary Neural Language Models. [[pdf]](docs/2015/Strategies for Training Large Vocabulary Neural Language Models.pdf) [url]
• Towards Universal Paraphrastic Sentence Embeddings. [url]
• Visualizing and Understanding Neural Models in NLP. [url]