Machine Learning Coursework

ML tutorials and implementations covering core algorithms and techniques.

📁 Structure

Folder	Contents
01-Fundamentals/	ML basics, model evaluation
02-Supervised-Learning/	Decision Trees, KNN, Linear & Logistic Regression, SVM
03-Unsupervised-Learning/	K-Means, PCA
04-NLP/	Text processing, NLP, email classification, text vectorization
05-Recommender-Systems/	Collaborative filtering
06-Deep-Learning/	Neural networks, TensorFlow, Keras, transfer learning, and optimization techniques
07-Feature-Engineering-and-Pipelines/	Feature engineering, ML pipelines
08-Model-Deployment-and-MLOps/	Model deployment, FastAPI, Django, and MLOps principles
datasets/	Sample datasets (cancer, heart disease, titanic, wine)
Lectures/	Course materials

🧠 06-Deep-Learning/ Substructure

Subfolder	Contents
01-TensorFlow-and-Keras/	Keras regression, classification, and image recognition notebooks
02-Advanced-Topics/	Advanced neural network concepts (for future expansion)
03-Lectures/	Deep learning theory and advanced topics PDFs
datasets/	Datasets for deep learning models
models/	Trained models (GEM model, etc.)

🚀 Quick Start

git clone https://github.com/RK0297/Machine-Learning-Coursework.git
pip install jupyter numpy pandas scikit-learn matplotlib seaborn tensorflow
jupyter notebook

📖 Requirements

Python 3.7+ • Jupyter • NumPy • Pandas • Scikit-learn • TensorFlow

💡 Notes

• Each notebook is self-contained with explanations and comments
• Datasets are included for immediate hands-on practice
• Some notebooks include AI-generated code examples for reference
• Models are saved in .h5 format for reproduction

---

Author: Radhakrishna Bharuka

Last Updated: June 2026

---

📝 Recent Changes

• ✅ Reorganized folder structure with consistent numbering (01-08)
• ✅ Renamed and organized Deep Learning subdirectories
• ✅ Standardized file naming conventions across all notebooks and models
• ✅ Created dedicated lecture materials folder with renamed PDFs