Machine Learning From Scratch

This project implements fundamental machine learning algorithms from scratch using Python and NumPy.

The goal is to understand how machine learning models learn through mathematical foundations and optimization techniques, without relying on high-level ML libraries.

Topics Covered

• Linear regression
• Logistic regression
• Gradient descent
• Cost and loss functions
• Model training and evaluation
• Basic neural network concepts
• Data preprocessing

Technologies

• Python
• NumPy
• Pandas
• Matplotlib
• Jupyter Notebook

Purpose

This project was created as part of my machine learning learning path and university work. It helped me understand how ML algorithms work internally, especially optimization, predictions, and evaluation.

What I Learned

• How gradient descent updates model parameters
• Difference between loss and cost functions
• How linear and logistic regression are implemented mathematically
• How to evaluate model performance
• Why mathematical foundations are important for AI systems

Relevance

This project supports my interest in artificial intelligence, machine learning engineering, and AI-native systems such as search, ranking, and recommendation systems.