Pytorch Study

파이토치 스터디

관심있는 모든 것(NLP, Generative Model, RL,...)을 더욱 잘 이해하기 위해 코드로 구현해보기 클래식한 모델부터 논문, 튜토리얼, 강의, 블로그를 읽고 이해한 것을 바탕으로 구현해보기 +_+

언젠가 직접 모델링하는 그 날까지...

파이썬 3.5 Pytorch 환경 구축해둔 도커

ubuntu 16.04 python 3.5.2 with various of ML/DL packages including tensorflow, sklearn, pytorch

docker pull dsksd/deepstudy:0.2

1. Deep NLP Models

1. BoWClassifier
2. NGRAM & CBOW
3. LSTM POS Tagger
4. Bidirectional LSTM POS Tagger
5. LSTM batch learning
6. Vanilla Sequence2Sequence (Encoder-Decoder)
7. Sequence2Sequence with Attention
8. Relational Network for bAbI task(in progress)
9. Transformer(Attention is all you need)

읽고 구현해보고 싶은 논문 리스트

1. Poincaré Embeddings for Learning Hierarchical Representations
2. Neural Embeddings of Graphs in Hyperbolic Space
3. A Deep Reinforced Model for Abstractive Summarization
4. Controllable Text Generation
5. A simple neural network module for relational reasoning

2. Generative Models

1. Basic Auto-Encoder
2. Regularized Auto-Encoder
3. Variational Auto-Encoder 3-1. Appendix1: Entropy and KL-divergence
4. Variational Reccurent Auto-Encoder

3. Reinforcement Learning

4. Evolutionary Algorithms