Introduction, AI Ethics and Society

• Read the 2021 AI100 Study Panel Report (esp. page 1-3, 7-11)

• Textbook Chapter 1 through the end of Section 1.1 (Rest of Chapter 1 is optional - we recommend skimming it at least)
• Textbook Chapter 2.1-2.3

• If you don't have a CS UNIX account (e.g. because you're a non-CS major), sign up for a temporary account IMMEDIATELY!

• Project 0: Unix/Python/Autograder tutorial

Search

• Textbook Chapter 3

• Homework 1: Search

• Project 1: Search in Pacman

Constraint Satisfaction Problems and Local Search

• Textbook Chapter 6
• Textbook Sections 4.1 and 4.2 (Rest of Chapter 4 is optional - we recommend skimming it at least)

• Homework 2: CSPs, Games, Utilities

Adversarial Search, Utilities

• Textbook Chapter 5 through the end of Section 5.5 (Rest of chapter 5 is optional - we recommend at least skimming it)
• Textbook Chapter 16 through the end of Section 16.3

• Project 2: Multi-Agent Pacman

Markov Decision Processes

• Textbook Chapter 17 through the end of Section 17.3
• Sutton and Barto Chapters 3 and 4

• Homework 3: MDPs, Reinforcement Learning

Midterm I, Reinforcement Learning I

• 2-hour exam on Gradescope which can be completed in a 40-hour window

• Project 3: Reinforcement Learning

Reinforcement Learning II, Probability

• Textbook Chapter 21
• Sutton and Barto Sections 6.1, 6.2, and 6.5

• Homework 4: Probability, Bayes Nets

Bayes Nets: Representation, Independence

• Textbook Chapter 14 through the end of Section 14.5

• Project 4: Bayes Nets

Bayes Nets: Inference, Sampling

• Final Project: Capture the Flag (Optional)

Hidden Markov Models, Particle Filters

• Textbook Chapter 15 through the end of Section 15.3.
• Textbook Section 15.4 is optional (we recommend skimming it at least)
• Textbook Chapter 15.5

• Homework 5: HMMs, Particle Filtering, Naive Bayes, ML Concepts

• Project 5: Ghostbusters

Midterm II, CoRL week (no class)

• 2-hour exam on Gradescope which can be completed in a 40-hour window

Decision Networks, Naive Bayes

• Textbook Sections 16.5 and 16.6
• Textbook Chapter 18 through the end of Section 18.2
• Skim Sections 18.3, but pay attention to the definition of overfitting in 18.3.5.
• Section 18.4
  • Section 18.5 is optional
• Textbook Chapter 20 through the end of Section 20.2
  • You can skim 20.2.3 if you're not comfortable with reasoning about continuous distributions (e.g. Gaussians).
  • 20.2.5 is just an overview without all the details - do your best.
  • Textbook Section 20.3 is optional

• Homework 6: Perceptons, Neural Networks, Gradient Descent

• Project 6: Classification

Perceptrons, Clustering, Deep Learning

• Section 18.6 except Sections 18.6.2
  • Sections 18.6.2 is optional
• Sections 18.7, 18.8, 18.9, and 18.11.
  • Section 18.10 is optional.

Thanksgiving (no class)

Guest Lecture, Conclusion

• Textbook Chapters 26 and 27

Final Exam