Understanding Artificial Intelligence
My works for understanding ai papers, ai projects, etc.
Implemented Papers
- Representation Learning with Contrastive Predictive Coding
- Attention Is All You Need
- A Structured Self-Attentive Sentence Embedding
- Training RNNs as Fast as CNNs (Single Recurrent Unit)
- TagSpace: Semantic Embeddings from Hashtags
Personal Research
Notes on papers
Note or summarization on papers using Github Issues starting from January 29, 2018
(inspired by kweonwooj/papers)
For convenience of searching the notes on paper
Paper List
- Eliminating All Bad Local Minima from Loss Landscapes Without Even Adding an Extra Unit
- Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual transfer and Beyond
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Subspace match probably does not accurately assess the similarity of learned representations
- Representation Learning with Contrastive Predictive Coding
- Neural Discrete Representation Learning
- A Quantum Many-body Wave Function Inspired Language Modeling Approach
- Self Imitation Learning
- Local sparsity control for Naive Bayes with extreme misclassiication costs
- What you get is what you see: A visual markup decompiler
- A Simple Method for Commonsense Reasoning
- Relational recurrent neural networks
- Language Modeling with Gated Convolutional Networks
- A Hybrid Convolutional Variational Autoencoder for Text Generation
- Asynchronous Methods for Deep Reinforcement Learning
- Dual Learning for Machine Translation
- An Empirical Evaluation of generic Convolutional and Recurrent Networks for Sequence Modeling
- Neural Machine Translation in Linear Time
- Learning to Generate Reviews and Discovering Sentiment
- Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types
- Neural Voice Cloning with a Few Samples
- Diversity Is All You Need: Learning Skills without a Reward Function
- Non-Autoregressive Neural Machine Translation
- Generating Wikipedia By Summarizing Long Sequences
- Zero-Shot Super-Resolution using Deep Internal Learning
- Convolution Sequence to Sequence Learning
- Bi-Directional Block Self-Attention for fast and memory-efficient sequence modeling
- Convolution Sequence to Sequence Learning