# MATH

## ProbStat

1. Frequentist vs Bayesian


2. Covariance and (in)dependent


3. Probabilistic and deterministic models


4. Multimodal and multivariate


5. Non-Normal Distribution to Normal Distribution

[Link](https://aegis4048.github.io/transforming-non-normal-distribution-to-normal-distribution)

6. t-distribution


[Link](https://datascience.stackexchange.com/questions/62958/when-to-use-t-distribution-instead-of-normal-distribution)

7. Density estimation

[Link](http://faculty.washington.edu/yenchic/17Sp_403/Lec7-density.pdf)

## NLP

- N-gram model: [link](https://web.stanford.edu/~jurafsky/slp3/3.pdf)
- N-gram vs neural net: [link](https://stackoverflow.com/questions/39708567/word-prediction-neural-net-versus-n-gram-approach#:~:text=The%20neural%20net%20will%20perform,predict%20requires%20a%20probability%20calculation.)
- Word embedding: [link](https://viblo.asia/p/so-luoc-word-embedding-gDVK2RAeKLj)
- Case-sentitive: [link](https://stackoverflow.com/questions/56384231/case-sensitive-entity-recognition)
- BLEU and WER: [link](https://viblo.asia/p/tim-hieu-ve-bleu-va-wer-metric-cho-1-so-tac-vu-trong-nlp-Eb85oA16Z2G)
- ROUGE: