- The Illustrated GPT-2 (Visualizing Transformer Language Models) [link]
- How to start a speech [link]
- Who would you bet on? [link]
- Hierarchical LDA python implementation [link]
- Found this very clear youtube tutorial on Dirichlet Process (unfortunately only in Chinese) [link]
- Topic Modeling with LSA, PLSA, LDA & lda2Vec. [link] [back-up copy]
- A very good tutorial that goes through the idea behind the generalization bound via VC dimension. [link] [back-up copy 1] [back-up copy 2]
- A good tutorial on transformers. [link]
- An overview of multi-task learning [link]