- code2vec: Learning Distributed Representations of Code [YT]
- Machine Learning for a Better Developer Experience [Medium]
- DSL Development with Xtext [vimeo]
- Life of a Netflix Partner Engineer — The case of the extra 40 ms [Medium]
- How to spin your scientific research out of a university and into a startup [YC]
- Adaptive correction of program statements [ACM]
- Compiling techniques to exploit the pattern of language usage [link]
- Natural information processing [link]
- NeuralQA: A Usable Library for Question Answering (Contextual Query Expansion + BERT) on Large Datasets [arXiv]
- T2API: Synthesizing API Code Usage Templates from English Texts with Statistical Translation [ACM]
- NLP2Code: Code Snippet Content Assist via Natural Language Tasks [arXiv]
- CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison [arXiv]
- Self-Training for Biomedical Parsing [link]
- How Will You Measure Your Life? [HBR]
- Quantum Computing for Pattern Classification [arXiv]
- Mining Change Logs and Release Notes to Understand Software Maintenance and Evolution [ResearchGate]
- Network In Network [arXiv]
- ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases [arXiv]
- Deep learning on unseen data: introducing federated learning [link]
- U-Net: Convolutional Networks for Biomedical Image Segmentation [arXiv] [Medium]
- Consistent Individualized Feature Attribution for Tree Ensembles [arXiv]
- Practical DevOps for the busy Data Scientist [link]
- Human-level control through deep reinforcement learning [nature]
- Deep Reinforcement Learning that Matters (! with interesting Conclusion and Supplementary)[arXiv]
- Self-Supervised Representation Learning [github.io]
- Learning to Predict Without Looking Ahead: World Models Without Forward Prediction [github.io]
- Demonstration of Machine Learning-Based Model-Independent Stabilization of Source Properties in Synchrotron Light Sources [PhysRevLet]
- Accelerated Methods for Deep Reinforcement Learning [arXiv]
- Reproducible Research is more than Publishing Research Artefacts: A Systematic Analysis of Jupyter Notebooks from Research Articles [arXiv]
- Self-training with Noisy Student improves ImageNet classification [arXiv]
- Putting An End to End-to-End: Gradient-Isolated Learning of Representations [arXiv]
- A Public Domain Dataset for Human Activity Recognition Using Smartphones [link] [dataset]
- Human Activity Recognition on Smartphones with Awareness of Basic Activities and Postural Transitions [Springer, p. 177] [dataset]
- ETSI GS Quantum Key Distribution (QKD); Application Interface [link]
- Maximal Adaptive-Decision Speedups in Quantum-State Readout [APS]
- Decision Making Photonics Solving Bandit Problems Using Photons [ResearchGate]
- A Reinforcement Learning approach for Quantum State Engineering [arXiv]
- Stable Baselines Tutorial [github.io]
- Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning [github.io]
- Semantic Versioning [link]
- State representation in Reinforcement Learning [stackexchange]
- Troubleshooting Deep Neural Networks [link]
- Architectural Principles for a Quantum Internet [IETF]
- A Link Layer Protocol for Quantum Networks [arXiv]
- A Neural Algorithm of Artistic Style [arXiv]
- Employee Turnover Prediction with Machine Learning: A Reliable Approach [ResearchGate]
- Machine Learning: The High Interest Credit Card of Technical Debt [ai.google]
- Seamless Nudity Censorship: an Image-to-Image Translation Approach based on Adversarial Training [ResearchGate]
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks [arXiv] [code]
- XLNet: Generalized Autoregressive Pretraining for Language Understanding [arXiv]
- Towards an Empirical Foundation for Assessing Bayesian Optimization of Hyperparameters [link] [set of benchmark functions provided in the paper were used to benchmark scikit-optimize]
- Unsupervised Data Augmentation for Consistency Training [arXiv]
- Learning hard quantum distributions with variational autoencoders [nature]
- A fully programmable 100-spin coherent Ising machine with all-to-all connections [science]
- Neural-network quantum state tomography [nature]
- Deep learning with coherent nanophotonic circuits [nature]
- Quantum Kitchen Sinks: An algorithm for machine learning on near-term quantum computers [arXiv]
- Solving the Quantum Many-Body Problem with Artificial Neural Networks [arXiv]
- QVECTOR: an algorithm for device-tailored quantum error correction [arXiv]
- A Quantum Approximate Optimization Algorithm [arXiv]
- A variational eigenvalue solver on a quantum processor [arXiv]
- Quantum principal component analysis [arXiv]
- Quantum Artificial Life in an IBM Quantum Computer [nature]
- A Software Methodology for Compiling Quantum Programs [arXiv]
 |
NLP | RL |
|---|---|---|
| 2017 fall | [Deep Learning in NLP] | [Deep Reinforcement Learning] |
| 2017 spring | [Deep learning in NLP] | - |
- Policy Gradient Methods for Reinforcement Learning with Function Approximation [nips]
- The CHEMDNER corpus of chemicals and drugs and its annotation principles [PubMed Central]
- Emotion Recognition From Speech With Recurrent Neural Networks [arXiv]
- Convolutional neural networks for artistic style transfer [post]
- SQuAD: 100,000+ Questions for Machine Comprehension of Text [arXiv]
- MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text [microsoft]
- DRAGNN: A Transition-based Framework for Dynamically Connected Neural Networks [arXiv]
- Generative Adversarial Nets [arXiv]
- The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology [oncotarget]
- Adversarial Autoencoders [arXiv]
- Latent Intention Dialogue Models [link]
- {+} Annotated Chemical Patent Corpus: A Gold Standard for Text Mining [link]
- Event-based text mining for biology and functional genomics [link]
- OSCAR4: a flexible architecture for chemical text-mining [link]
- Word Representations via Gaussian Embedding [arXiv]
- Gaussian Mixture Embeddings for Multiple Word Prototypes [arXiv]
- Multimodal Word Distributions [arXiv]
- Canonical Correlation Analysis For Classifying Baby Crying Sound Events [link]
- Seq2seq-Attention Question Answering Model [link]
- Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models [ResearchGate]
- Attention Is All You Need [arXiv]
- What is a variational autoencoder? [post]
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention [arXiv]
- Attention and Memory in Deep Learning and NLP [link]
- Turing Computation with Recurrent Artificial Neural Networks [arXiv]
- How to Code and Understand DeepMind's Neural Stack Machine [post]
- SimpleDS: A Simple Deep Reinforcement Learning Dialogue System [arXiv]
- On the universal structure of human lexical semantics [PNAS]
- Understanding LSTM Networks [post]
- Recurrent Neural Network Grammars [arXiv]
- Explaining and illustrating orthogonal initialization for recurrent neural networks [post]
- Massive Exploration of Neural Machine Translation Architectures [arXiv]
- The Greening of Blockchains [post]
- Reinforcement Learning for Trading [link]
- Image Style Transfer, Neural Doodles & Texture Synthesis [YT] [slides]
- Distributed Representations of Sentences and Documents [link]
- Stock Trading with Recurrent Reinforcement Learning (RRL) [link] [working code]
- Reinforcement Learning for Market-Making [YT]
- New Territory of Machine Translation [YT]
- A Multiagent Approach to Q-Learning for Daily Stock Trading [link]
- A genetic algorithm enabled ensemble for unsupervised medical term extraction from clinical letters [link]
| |
NLP | RL |
|---|---|---|
| 2016 fall | [Natural language processing] | [Reinforcement learning] |