This repository contains implementations of various algorithms, models, and systems built entirely from scratch. The goal is to deepen understanding of how things work at a fundamental level by recreating them without using pre-built libraries or frameworks for the core functionality.

"What I cannot create, I do not understand" - Richard Feynman

A simple chatbot implementation built from the ground up to understand the fundamentals of natural language processing and conversation flows.

• ✅ Text processing and tokenization
• ✅ Pattern matching for responses
• ✅ Basic context awareness
• ✅ Simple conversation memory

An implementation of the YOLOv1 (You Only Look Once) object detection algorithm, built from scratch to understand the mechanics of single-shot object detection.

• ✅ Custom neural network architecture
• ✅ Bounding box prediction
• ✅ Object classification
• ✅ Non-max suppression
• ✅ Training and inference pipelines

This project is dedicated to building classic machine learning models without using libraries like scikit-learn or TensorFlow — only NumPy and core Python.

• ✅ K-Nearest Neighbors (KNN)
• ⏳ Linear Regression
• ⏳ Logistic Regression
• ⏳ Decision Tree
• ⏳ Support Vector Machine (SVM)

• 📂 .py files for core model logic
• 📓 test.ipynb for experimenting with sklearn datasets like Iris, Digits, etc.
• 📊 Evaluation framework using accuracy, classification report, and confusion matrix

Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

Distributed under the MIT License. See LICENSE for more information.

Madhawa - @Madhawa2001

Project Link: https://github.com/username/made-from-scratch