Schedule

Note

We may adapt the course schedule to accomodate your learning!

Monday	Wednesday	Thursday
01 September Labor Day: no classes.	03 September Topic: What is Probabilistic ML? [slides] Vectorization Pre-Class: Read The Fear of Publicly Not Knowing Read the course syllabus Join the course on Gradescope Answer the syllabus survey on Gradescope by 5pm the day before---it's graded. Released: HW1: Vectorization	04 September Topic: Probability (Discrete) [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class.
08 September Topic: Conditional Probability (Discrete) [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class. Due: HW1: Vectorization (by midnight the night before) Released: HW2: Directed Graphical Models	10 September Topic: Lab	11 September Topic: Joint Probability (Discrete) [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class.
15 September Topic: Lab	17 September Topic: Lab Due: Checkpoint 2.1 (by midnight the night before)	18 September Topic: The Ethics of Data [slides] Pre-Class: Read the "Community Guidelines for Ethics Discussions," under "Goals and Expectations." Complete all readings listed in the corresponding chapter. Answer the corresponding questions to prepare for class discussions.
22 September Topic: Maximum Likelihood: Theory [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class. Due: HW2: Directed Graphical Models (by midnight the night before) Released: HW3: Frequentist Learning	24 September Topic: Lab	25 September Topic: Maximum Likelihood: Code [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class.
29 September Topic: Probability (Continuous) [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class. Due: Checkpoint 3.1 (by midnight the night before)	01 October Topic: Optimization [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class.	02 October Topic: The Ethics of Learning from Data [slides] Pre-Class: Complete all readings listed in the corresponding chapter. Answer the corresponding questions to prepare for class discussions. Due: Checkpoint 3.2 (by midnight the night before)
06 October Topic: Regression [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class. Due: HW3: Frequentist Learning (by midnight the night before) Released: HW4: Predictive Models	08 October Topic: Lab	09 October Topic: Classification [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class.
13 October Indigenous Peoples' Day: no classes.	15 October Topic: Neural Networks [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class. Due: Checkpoint 4.1 (by midnight the night before)	16 October Topic: Lab
20 October Topic: Model Selection & Evaluation [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class.	22 October Topic: Lab	23 October Topic: The Ethics of Predictive Models in Sociotechnical Systems [slides] Pre-Class: Complete all readings listed in the corresponding chapter. Answer the corresponding questions to prepare for class discussions. Due: Checkpoint 4.2 (by midnight the night before)
27 October Topic: Gaussian Mixture Models (Clustering) [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class. Due: HW4: Predictive Models (by midnight the night before) Released: HW5: Generative Models	29 October Topic: Lab	30 October Topic: Factor Analysis (Dimensionality Reduction) [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class.
03 November Topic: Lab Due: Checkpoint 5.1 and 5.3 (by midnight the night before)	05 November Topic: Lab	06 November Topic: Guest Lecture: Dr. Weiwei Pan on the Ethics of Generative Models in Sociotechnical Systems Pre-Class: Complete all readings listed in the corresponding chapter. Answer the corresponding questions to prepare for class discussions.
10 November Topic: Bayesian Models: Priors & Posteriors [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class. Due: HW5: Generative Models (by midnight the night before) Released: HW6: Bayesian Models	12 November Topic: Lab	13 November Topic: Bayesian Models: Posterior Predictive [slides] Pre-Class: Read corresponding chapter; prepare questions to ask in class. Extra-Credit: Attend the talk by Prof. Lindsey Cameron Time: November 14 at TBD Location: TBD Answer reflection quetsions on Gradescope
17 November Topic: Lab Due: Checkpoint 6.1 and 6.3 (by midnight the night before)	19 November Topic: Lab	20 November Topic: The Ethics of Uncertainty and Interpretability in Human-AI Systems [slides] Pre-Class: Complete all readings listed in the corresponding chapter. Answer the corresponding questions to prepare for class discussions.
24 November Topic: Guest Lecture Due: HW6: Bayesian Models (by midnight the night before) Released: HW7: The Ethics of Machine Learning	26 November Thanksgiving Break: no classes.	27 November Thanksgiving Break: no classes.
01 December Topic: Variational Autoencoders (VAEs) Due: Checkpoint 7.1 (by midnight the night before)	03 December Topic: Special Topics	04 December Topic: The Ethics of Machine Learning: A View from History (Part 1) [slides] Pre-Class: Complete all readings listed in the corresponding chapter. Answer the corresponding questions to prepare for class discussions. Due: Checkpoint 7.2 (by midnight the night before)
08 December Topic: The Ethics of Machine Learning: A View from History (Part 2) [slides] Pre-Class: Complete all readings listed in the corresponding chapter. Answer the corresponding questions to prepare for class discussions. Due: HW7: The Ethics of Machine Learning (by midnight the night before)	10 December Topic: Group Reflection [slides]	11 December Reading Period Begins.
15 December Final Exam Period Begins.	17 December	18 December

Acknowledgements: The schedule design and CSS is based on Fall 2018’s CS240’s schedule.