Many of the most successful inference and machine learning algorithms arise out of probabilistic modeling and analysis. If you want to learn the fundamentals of this discipline and see some of what you can do with it, this subject is the place to start.
6.008 provides a solid foundation for more advanced subjects that build on this framework of reasoning. As such, the subject is targeted at (and likely to strongly appeal to) students both across and beyond Course 6 (EECS).
Instructors: Polina Golland, Gregory W. Wornell, Lizhong Zheng
Prereq: Calculus II (GIR) or permission of instructor
Units: 4-4-4, Institute Lab
Lecture: MW10 (32-155)
Recitation: TR12 (35-308) or TR1 (34-302) or TR2 (34-302)
Introduces probabilistic modeling for problems of inference and machine learning from data, emphasizing analytical and computational aspects. Distributions, marginalization, conditioning, and structure; graphical and neural network representations. Belief propagation, decision-making, classification, estimation, and prediction. Sampling methods and analysis. Introduces asymptotic analysis and information measures. Computational laboratory component explores the concepts introduced in class in the context contemporary applications. Students design inference algorithms, investigate their behavior on real data, and discuss experimental results.
Updated content for Fall 2019 for introduction to neural network models for inference.
EECS students in 6-2 program can use 6.008 as one of their foundation subjects.
All EECS students can use 6.008 as one of their elective EECS subjects.
All EECS students may petition to take 6.008 instead of 6.042 as one of their math elective subjects and to use it as a prerequisite for more advanced subjects that require 6.042 (by petition; more details will be given in class).
6.008 can also be used by MEng students as one of their restricted elective subjects.
As usual, no double counting is allowed.