Machine Learning Specialization – Coursera

This repository contains my solutions and notes for the Machine Learning Specialization offered by DeepLearning.AI and Stanford University, taught by Andrew Ng.

This 3-course series provides a practical and theoretical foundation in Machine Learning using Python and Jupyter Notebook, with hands-on assignments and conceptual explanations.

---

Specialization Overview

Course 1: Supervised Machine Learning – Regression and Classification

Topics covered:

• Linear regression (univariate and multivariate)
• Logistic regression
• Gradient descent
• Feature scaling and normalization
• Overfitting and regularization
• Model evaluation (accuracy, precision, recall)

Folder: Course1/

---

Course 2: Advanced Learning Algorithms

Topics covered:

• Neural networks and deep learning
• Activation functions (ReLU, sigmoid, tanh)
• Forward and backward propagation
• Multiclass classification
• Decision trees and ensemble methods (random forests, boosting)

Folder: Course2/

---

Course 3: Unsupervised Learning, Recommenders, Reinforcement Learning

Topics covered:

• Clustering (k-means)
• Principal Component Analysis (PCA)
• Anomaly detection
• Recommender systems (collaborative filtering)
• Reinforcement learning basics
• Markov Decision Processes (MDPs)

Folder: Course3/