Stanford CS229 – Assignments and Projects

This repository contains selected assignments and small project implementations completed as part of Stanford CS229 (Machine Learning).

Contents

• Cocktail Party Problem
  Source separation and signal processing experiments.

• Tic-Tac-Toe (Reinforcement Learning)
  Reinforcement learning via self-play in a discrete, fully observable setting.

• Inverted Pendulum
  Classical control and reinforcement learning approaches to stabilization.

• Common ML Algorithms
  some Classical ML algorithms like regresssion, MLPs, naive bayes, knn and much more implemented completely from scratch

Each directory is self-contained and corresponds to an individual assignment or exploratory project.