Priority registration is over. Any student should be able to register for open space.

ALL sections named with 'UG'

FIELD OF STUDY - MAJOR

Priority registration is over. Any undergraduate student should be able to register for open space.

EXCEPTION: For STAT 427 1UG, see entry further down in table

Priority registration is over. Any graduate student should be able to register for open space.

EXCEPTION: For STAT 427 1GR, see entry further down in table

MATH 464 / STAT 410

MATH 469 / STAT 420

MATH 408 / STAT 408

MATH 469 / STAT 420

Topic: Stochastic Processes

Description: A stochastic process is a random process that represents the evolution of some system over time. The course is aimed at advanced undergraduate and beginning graduate students. Topics include discrete-time Markov chains, random walks, continuous-time Markov chains, Poisson processes, birth-and-death processes, renewal processes, queues, Brownian motion (Wiener process), and Ito's lemma.

Topic: Advanced Data Science

This section is NOT controlled by the Department of Statistics. It meets with INFO 490 section RB2 (CRN 64015) and IS 490 section RB2 (CRN 67578). Please contact INFO with any questions.

This class is an asynchronous, online course.

NOTE: Students must be registered by 4 pm on Wednesday January 17, 2018. No new students will be allowed to register for this class after that.

Description: This course will introduce advanced data science concepts by building on the foundational concepts presented in INFO 490: Foundations of Data Science. Students will first learn how to perform more statistical data exploration and constructing and evaluating statistical models. Next, students will learn machine learning techniques including supervised and unsupervised learning, dimensional reduction, and cluster finding. An emphasis will be placed on the practical application of these techniques to high-dimensional numerical data, time series data, image data, and text data. Finally, students will learn to use relational databases and cloud computing software components such as Hadoop, Spark, and NoSQL data stores. Students must have access to a fairly modern computer, ideally that supports hardware virtualization, on which they can install software. This class is open to sophomores, juniors, seniors and graduate students in any discipline who have either taken a previous INFO 490 data science course or have received instructor permission.

Topic: Statistical Learning in Data Science

Prerequisites: STAT 410 or STAT 510; and STAT 425

Description: Learn to analyze large complex data using advanced statistical learning methods and algorithms. Topics include data exploration and interpretation for structured and unstructured data; large data processing; optimization tools; recommender system; tensor methods; text mining; and imaging analysis. Software used includes R and Matlab. Students will gain practical skills of data mining and knowledge discovery in various applications such as business, political science, biology and medicine.

Topic: Bayesian Methods for Machine Learning

Prerequisites: STAT 410 or STAT 510; STAT 428 or STAT 525; and STAT 542.

Description: The course aims to give a solid introduction to the theory, methods and computation of Bayesian inference, with a view toward applications in data mining and machine learning. Topics include Bayesian model selection and averaging, Bayesian netwoks and structure learning, Approximate Bayesian Computational methods, Bayesian nonparametrics, and Bayesian optimization.

Registration for STAT 593 requires instructor approval.

To seek instructor approval, see here: http://go.illinois.edu/stat593

Registration for STAT 593 without instructor approval will result in a failing grade.