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
- BoWClassifier
- NGRAM & CBOW
- LSTM POS Tagger
- Bidirectional LSTM POS Tagger
- LSTM batch learning
- Vanilla Sequence2Sequence (Encoder-Decoder)
- Sequence2Sequence with Attention
- Relational Network for bAbI task(in progress)
- Transformer(Attention is all you need)
읽고 구현해보고 싶은 논문 리스트
- Poincaré Embeddings for Learning Hierarchical Representations
- Neural Embeddings of Graphs in Hyperbolic Space
- A Deep Reinforced Model for Abstractive Summarization
- Controllable Text Generation
- A simple neural network module for relational reasoning
2. Generative Models
- Basic Auto-Encoder
- Regularized Auto-Encoder
- Variational Auto-Encoder 3-1. Appendix1: Entropy and KL-divergence
- Variational Reccurent Auto-Encoder