1. The AI world
2. Logistics of the course
3. Presentation of the Syllabus

Week 1 and Week 2 of Supervised Machine Learning: Regression and Classification (including optional labs and quizzes)

1. Linear Regression
2. Derivations
3. Practice problems

Week 3 of Supervised Machine Learning: Regression and Classification (including optional labs and quizzes)

1. Logistic Regression
2. Text processing
3. Derivations
4. Practice problems

Week 1 of Advanced Learning Algorithms: Neural Networks (including optional labs and quizzes)

1. Neural Networks
2. Vectorized Gradients
3. Softmax
4. Practice problems

Week 2 of Advanced Learning Algorithms: Neural network training (including optional labs and quizzes)

Project Proposal

1. Multi-class classification
2. Vectorized Back-propagation
3. Practice problems

Week 3 of Advanced Learning Algorithms: Advice for applying machine learning (including optional labs and quizzes)

1. Bias & Variance Trade-off in Practice
2. Practice problems
3. Debugging Strategies for Final Project
4. Advice on ML Systems
5. Hogwarts Case study.

Week 4 of Advanced Learning Algorithms: Decision trees (including optional labs and quizzes)

1. Measuring Purity
2. Random Forest
3. XG Boost
4. Practice problems

Week 1 of Unsupervised Learning, Recommenders, Reinforcement Learning: Unsupervised Learning (including optional labs and quizzes)

Midterm will be held during class time. Check out to Midterm FAQ (#5) on Ed for more details.

Week 2 of Unsupervised Learning, Recommenders, Reinforcement Learning: Recommender Systems (including optional labs and quizzes)

Project Milestone (Due March 8)

1. K-Means Clustering
2. Principal Component Analysis

Week 3 of Unsupervised Learning, Recommenders, Reinforcement Learning: Reinforcement Learning (including optional labs and quizzes)

1. AI future directions and Career Advice with Andrew

Final Report and PSET 3 due. Poster is due the day before.