CS 274A: Probabilistic Learning: Theory and Algorithms


General Information

Course Goals
Students will develop a comprehensive understanding of probabilistic approaches to machine learning, a key component underlying areas such as artificial intelligence, natural language processing, speech recognition, computer vision, bioinformatics, and so forth. The course will provide a tutorial introduction to the basic principles of probabilistic modeling and then demonstrate the application of these principles to the analysis, development, and practical use of machine learning algorithms. Topics covered will include probabilistic modeling, defining likelihoods, parameter estimation using likelihood and Bayesian techniques, probabilistic approaches to classification, clustering, and regression, and related topics such as model selection and bias/variance tradeoffs. Discussion of topics such as deep learning, generative models, and large language models will be incorporated where relevant.

Background Knowledge
Knowledge of basic concepts in probability, multivariate calculus, and linear algebra are important for this course. In particular a good understanding of basic concepts in probability (conditional probability, expectation, multivariate probability models, density functions, etc) is important. If you are not sure whether you have the relevant background or not, please take a look at Chapters 5.1 to 5.5 and 6.1 to 6.5 in Mathematics for Machine Learning: its fine if you have not seen all of this material before, but it will be helpful for this class if you are fairly comfortable with the level of notation and mathematics used in these chapters.

Homeworks

Grading Policy
Final grades will be based on a combination of homework assignments and exams: 40% homeworks, 30% midterm, and 30% final. Your lowest scoring homework will be dropped and not included in your score. No credit for late homeworks.

Academic Integrity
Students are expected to read and be familiar with the Academic Integrity Policy for this class. Failure to adhere to this policy can result in a student receiving a failing grade in the class.