Skip to content
View hien078's full-sized avatar
2 followers · 2 following

Block or report hien078

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please donโ€™t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
hien078/README.md

Hi, I'm Hiแป‡n ๐Ÿ‘‹

๐ŸŽ“ Applied Mathematics student at USTH (University of Science and Technology of Hanoi) ๐Ÿ”ฌ AI / ML Researcher & Mathematical Software Engineer โ€” bridging rigorous mathematics and modern machine learning ๐Ÿ“ Building knowledge from first principles: derive mathematically, code from scratch, and verify empirically.

๐ŸŒŸ Flagship Project

๐Ÿค–

Machine-Learning-from-scratch

22 ML & Deep Learning algorithms โ€” derived by hand, implemented in pure NumPy & PyTorch, verified by tests.

CI Docs License: MIT Python

  • 22 topics in five phases: OLS โ†’ SVM โ†’ Random Forest โ†’ CNN โ†’ LSTM โ†’ Transformer โ†’ VAE/Diffusion โ†’ RL โ†’ GNN โ†’ LLM engineering (BPE/LoRA/DPO) โ†’ SSL
  • Every topic = theory.md derivation + from-scratch notebook + exercises, backed by an installable library with 65 unit tests, 85% coverage floor, and CI-executed notebooks
  • ๐Ÿ“– Read it as a website: hien078.github.io/Machine-Learning-from-scratch

The rest of the first-principles trilogy:

  • ๐Ÿงฎ applied-mathematics-foundation โ€” the math prerequisites: Linear Algebra, Calculus, Probability & Statistics, Optimization, Information Theory, ODEs, Graph Theory, Numerical Methods
  • ๐Ÿ“ first-principles-math-modeling โ€” 15 modeling topics: dynamical systems, SIR epidemics, game theory, LP/IP/KKT optimization, simulation โ€” 121 Colab-ready notebooks

๐Ÿ”ฌ Research & Engineering Focus

  • Mathematical Foundations of Deep Learning: Convex & non-convex optimization, matrix calculus, spectral theory.
  • Neural ODEs & Dynamical Systems: Physics-Informed Neural Networks (PINNs), continuous-time models.
  • First-Principles ML: Building transparent, scalable ML algorithms from scratch without black-box abstractions.
  • Information & Optimization Theory: Variational inference, ELBO bounds, information geometry.

๐Ÿ› ๏ธ Tech Stack & Tools

  • Languages & Frameworks: Python PyTorch NumPy SciPy Pandas scikit-learn
  • Math & Authoring: LaTeX KaTeX JupyterLab Matplotlib Plotly
  • DevOps & OS: Git GitHub Actions GitHub CLI Linux (Bash) VS Code

๐Ÿ“Š GitHub Stats

Hien's GitHub Stats Top Languages

"The purpose of computing is insight, not numbers." โ€” Richard Hamming

Popular repositories Loading

  1. Machine-Learning-from-scratch Machine-Learning-from-scratch Public

    ๐Ÿค– 22 ML & Deep Learning algorithms derived mathematically and implemented from scratch in pure NumPy & PyTorch โ€” OLS, SVM, Random Forest, CNN, LSTM, Transformer, VAE, RL, GNN, LLM (BPE/LoRA/DPO) + โ€ฆ

    Jupyter Notebook 1

  2. first-principles-math-modeling first-principles-math-modeling Public

    ๐Ÿ“ First-principles mathematical modeling โ€” 15 topics: dynamical systems, SIR epidemic models, ODEs, optimization, game theory, simulation & data-driven modeling. All with Jupyter notebooks.

    Jupyter Notebook 1

  3. applied-mathematics-foundation applied-mathematics-foundation Public

    ๐Ÿงฎ Rigorous applied mathematics for AI & Data Science โ€” 8 comprehensive modules: Linear Algebra, Calculus, Probability & Statistics, Optimization, Information Theory, ODEs, Graph Theory, Numerical Mโ€ฆ

    Jupyter Notebook 1

  4. hien078 hien078 Public