Skip to content
View hoanglechau's full-sized avatar
😎
Working Hard
😎
Working Hard
13 followers · 31 following
  • Ho Chi Minh City, Vietnam

Achievements

Achievement: YOLOAchievement: Pull Sharkx2

Achievements

Achievement: YOLOAchievement: Pull Sharkx2

Block or report hoanglechau

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 don’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 user’s behavior. Learn more about reporting abuse.

Report abuse
hoanglechau/README.md

Hi 👋, I'm Hoang 😎

A passionate AI Researcher and Educator

⭐ Programming Languages: Python, Java, JavaScript, C, C++, SQL, HTML, CSS.

⭐ Language Proficiencies: English (C2 Level - IELTS Academic 8.5/9.0 with 8.5/9.0 in Speaking, TOEFL iBT 6/6 with 6/6 in Speaking and Writing, TOEIC 990/990), Japanese (B1 Level - JLPT N3), Mandarin (Intermediate), Vietnamese (Native), German (Elementary), French (Elementary).

⭐ Deep Learning & Computer Vision: PyTorch, TensorFlow, Keras, SAM (Segment Anything Model), MedSAM, OpenCV, Transfer Learning, Multi-Task Learning, ResNet/SE-ResNet Architectures.

⭐ Medical Image Analysis: 2D/3D Segmentation, Denoising, Artifact Simulation (Gaussian/Poisson), DICOM Data Handling, Evaluation Metrics (Dice, Hausdorff Distance, IoU).

⭐ Machine Learning & Data Science: Scikit-learn, Pandas, NumPy, SciPy, Class Imbalance Handling (SMOTE), Feature Selection (mRMR), Hyperparameter Tuning (GridSearchCV), Clustering (K-Means).

⭐ Mathematical Foundations: Linear Algebra, Calculus, Probability & Statistics, Optimization Algorithms, Loss Function Design (Hard Parameter Sharing).

⭐ Research & MLOps Tools: Git/GitHub, Experiment Tracking, Docker, Google Colab, Linux/Bash, LaTeX, Scientific Visualization (Matplotlib, Seaborn).

⚡ Languages and Tools ⚡

python cpp java javascript typescript react redux nodejs express mongodb postman linux nginx

html5 css3 bootstrap materialui chakraui npm vite webpack babel eslint

vscode neovim webstorm pycharm git github bitbucket gitlab netlify gcp

jupyternotebook anaconda figma jira trello slack discord zoom

Pinned Loading

  1. benchmarking-sam-noisy-abdominal-ct benchmarking-sam-noisy-abdominal-ct Public

    A comprehensive benchmark study evaluating the robustness of Segment Anything Model (SAM) and its medical domain adaptation (MedSAM) under realistic noisy medical imaging conditions.

    Jupyter Notebook

  2. multi-task-learning-dl multi-task-learning-dl Public

    This project implements a Multi-Task Learning (MTL) deep learning model that simultaneously predicts three independent targets from 32x32 grayscale images.

    Jupyter Notebook

  3. channelwise-attention-residual-networks-dl channelwise-attention-residual-networks-dl Public

    This project implements a Squeeze-and-Excitation Residual Network (SE-ResNet) to solve a fine-grained classification problem on 32 × 32 images. It addresses signal-to-noise challenges in low-resolu…

    Jupyter Notebook

  4. ensemble-sentiment-analysis-system-nlp ensemble-sentiment-analysis-system-nlp Public

    A full-stack Ensemble Sentiment Analysis System built with Flask, MongoDB, and Docker. Features AI-powered review classification using ensemble machine learning models and provides a comprehensive …

    Python

  5. multi-objective-session-based-recommender-system-ml multi-objective-session-based-recommender-system-ml Public

    Implementation of a high-performance Two-Stage Recommender System designed to predict user intent (Clicks, Cart Additions, Orders) from anonymous, short-session e-commerce data.

    Jupyter Notebook

  6. optimizing-ecommerce-revenue-ds optimizing-ecommerce-revenue-ds Public

    A predictive ML pipeline to classify online shoppers’ purchase intent and segment customer types – leveraging SMOTE to address class imbalance, applying mRMR for feature selection, and training mul…

    Jupyter Notebook