Machine Learning Specialization

Contains my solutions and notes for the Machine Learning Specialization by Stanford University & DeepLearning.AI on Coursera, taught by Andrew Ng.

Course 1: Supervised Machine Learning: Regression and Classification

• Week 1: Introduction to Machine Learning, Linear Regression, Cost Function, Gradient Descent
• Week 2: Multiple Linear Regression, Feature Scaling, Feature Engineering, Polynomial Regression
• Week 3: Logistic Regression, Decision Boundary, Cost Function for Logistic Regression, Overfitting & Regularization

Course 2: Advanced Learning Algorithms

• Week 1: Neural Networks, TensorFlow, Neural Network Implementation
• Week 2: Neural Network Training, Activation Functions, Multiclass Classification, Softmax
• Week 3: Advice for Applying Machine Learning, Bias/Variance, Machine Learning Development Process
• Week 4: Decision Trees, Tree Ensembles, Random Forest, XGBoost

Course 3: Unsupervised Learning, Recommenders, Reinforcement Learning

• Week 1: K-Means Clustering, Anomaly Detection
• Week 2: Collaborative Filtering, Content-Based Filtering, Recommender Systems
• Week 3: Reinforcement Learning, State-Action Value Function, Continuous State Spaces

Specialization Certificate

Specialization Certificate

Repository Structure

Machine-Learning-Specialization/
├── C1-Supervised Machine Learning/
│   ├── Week 1/
│   ├── Week 2/
│   └── Week 3/
├── C2-Advanced Learning Algorithms/
│   ├── Week 1/
│   ├── Week 2/
│   ├── Week 3/
│   └── Week 4/
├── C3-Unsupervised Learning, Recommenders & Reinforcement Learning/
│   ├── Week 1/
│   ├── Week 2/
│   └── Week 3/
└── README.md

Disclaimer

The solutions and notes in this repository are meant for reference purposes only. Please attempt the assignments yourself before consulting them—the real learning comes from working through the problems on your own.

Acknowledgements

• Andrew Ng for creating this exceptional specialization
• Stanford University & DeepLearning.AI for offering the course
• Coursera for hosting the platform