printer friendly pageCS 228: Probabilistic Graphical Models: Principles and Techniques
Probabilistic graphical modeling languages for representing complex domains, algorithms for reasoning using these representations, and learning these representations from data. Topics include: Bayesian and Markov networks, extensions to temporal modeling such as hidden Markov models and dynamic Bayesian networks, exact and approximate probabilistic inference algorithms, and methods for learning models from data. Also included are sample applications to various domains including speech recognition, biological modeling and discovery, medical diagnosis, message encoding, vision, and robot motion planning. Prerequisites: basic probability theory and algorithm design and analysis.
Terms: Win
|
Units: 3-4
|
Grading: Letter or Credit/No Credit
Instructors:
Koller, D. (PI)
CS 228T: Probabilistic Graphical Models: Advanced Methods
For students interested in advanced methods in machine learning and probabilistic AI. Describes the theoretical foundations for methods of inference and learning in probabilistic graphical models, allowing for the derivation of properties of these methods and for the development of more advanced methods. Sample topics include advanced methods in Markov chain Monte Carlo, approximate message-passing algorithms for inference derived from an optimization perspective, representation and inference in models involving continuous variables, learning undirected models, learning with hidden variables, and non-parametric Bayesian methods. Prerequisites:
CS228; strong mathematical foundation.
Terms: Spr
|
Units: 3
|
Grading: Letter or Credit/No Credit
Instructors:
Murphy, K. (PI)
CS 231B: The Cutting Edge of Computer Vision
(Formerly 223C) More than one-third of the brain is engaged in visual processing, the most sophisticated human sensory system. Yet visual recognition technology has fundamentally influenced our lives on the same scale and scope as text-based technology has, thanks to Google, Twitter, Facebook, etc. This course is designed for those students who are interested in cutting edge computer vision research, and/or are aspiring to be an entrepreneur using vision technology. Course will guide students through the design and implementation of three core vision technologies: segmentation, detection and classification on three highly practical, real-world problems. Course will focus on teaching the fundamental theory, detailed algorithms, practical engineering insights, and guide them to develop state-of-the-art systems evaluated based on the most modern and standard benchmark datasets. Prerequisites: CS2223B or equivalent and a good machine learning background (i.e.
CS221,
CS228,
CS229). Fluency in Matlab and C/C++.
Terms: not given this year
|
Units: 3
|
Grading: Letter or Credit/No Credit
Filter Results: