This repository contains materials, code, and papers for Phase 1 of the DSLab training program, part of the International Center BKAI.
Phase 1 training focuses on the fundamentals of Machine Learning and Deep Learning, with a practical emphasis on NLP. You can start practicing right away using the Google Colab badge above.
-
materials: Contains all lectures from the Machine Learning IT3190E course at HUST, taught by Assoc. Prof. Than Quang Khoat, Team Leader of DSLab. -
ss1: Season 1 focuses on preprocessing text documents with TF-IDF and Ridge Regression. -
ss2: Season 2 focuses on K-Means and SVM. -
ss3: Season 3 focuses on ANN. -
ss4: Season 4 focuses on time-series data, specifically RNNs.
Each season includes:
-
ss/data: Stores raw and processed data for training. -
ss/materials: Contains research papers. -
ss/src: Source code.
I am currently in Phase 2 of the DSLab training, which focuses on Probabilistic Graph Models and requires a substantial amount of mathematics, particularly in Probability and Statistics. I will occasionally update this repository with relevant content. If you are interested, I recommend the CS228 course on Probabilistic Graphical Models from Stanford.
If you are reading this README.md, you may be interested in joining DSLab. Application forms open in August each year on BKAI's Facebook page. The application process includes a 2-month waiting period for CV review, with announcements made in late September for successful applicants. The first interview takes place at the beginning of October, followed by a 3-month period of self-study in mathematics before the second interview. The entire process to become an official member of DSLab takes approximately 6 months.
Don't worry if you're not confident in your math skills; I wasn't either, but I still made it. Good luck, and I hope to see you soon at DSLab!