Course Syllabus

BASIC INFORMATION

Catalog information: Variable Credits; no prerequisite

Time and Place: MWF 4th Period, CSE E118

Instructor: Raphael T. Haftka (haftka@ufl.edu), Nam-Ho Kim (nkim@ufl.edu)

Raphael T. Haftka: 220 MAE-A. Office hours: TR 8^th period, F 9^th period.

Nam-Ho Kim: 210 MAE-A. Office hours: MWF 9^th period.

Teaching assistant: Shu Shang 333 MAE-A, ss0719@ufl.edu. Office hours TBD

Textbooks: None

References: 

Choi, Grandhi, and Canfield, Reliability-based Structural Design, Springer, 2007 (electronic book available from UF library).

Oberkampf and Roy, Verification and Validation in Scientific Computing, Cambridge University Press, 2010.

Gelman, Carlin, Stern, and Rubin, Bayesian Data Analysis, Chapman and Hall/CRC, 1995.

Objective: Introduce students to uncertainty quantification and reduction and its use for reliability based design, verification and validation.

Catalog Information: Uncertainty, Bayesian statistics and surrogates. Reliability and optimization under uncertainty. Verification and validation. Prerequisite: Graduate standing in Science or Engineering.

Topics:

The course is divided into three modules. Students can take different modules with variable credits. Each module has an exam and will be given one credit.

1. Bayesian techniques

• Bayes rule and Bayesian inference
• Bayesian estimation
• Markov chain Monte Carlo

2. Surrogates and design under uncertainty

• Surrogates construction and accuracy assessment
• Reliability estimation
• Design under uncertainty

3. Verification and validation under uncertainty

• Verification and validation fundamentals
• Statistical calibration
• Validation metrics

COURSE ASSESSMENT

Homework: Problems from last year’s assignments will be posted with solutions, often as links on the Power Point slides of the lectures. Homework will consist of inventing or finding useful additional problems and submitting them with detailed solutions. These will be graded on clarity (50%), usefulness (30%) and originality (20%), with points deducted for mistakes depending on their severity. The best submissions will be selected and posted for an extra 10% bonus. Furthermore, the module exams will typically feature one of these posted problems, possibly with different numbers. Homework may be submitted with no late penalty by Canvas. After that, there is 10% penalty per day.

Exams: All exams are closed book, except for one 8.5"x11" page, written in any density (student may bring a magnifier). There are three in-term exams. Quizzes are closed book.

Project: There will be a project for the verification and validation module.

Grading Policy: The final grade will be based on an average giving 100 points for each module and 50 points to the project. For each module the grade will be 50% exam, 30% homework and 20% quizzes. Grades are on an absolute scale A = 93, A- = 90, B+ = 87, B = 83, B- = 80, C+ = 77, C = 73, C- = 70, D+ = 67, D = 63, D- = 60), with minor adjustments to avoid grades being decided by a small fraction of a point).

Re-grading Policy: Any re-grade requests must be submitted in writing within ONE WEEK after return of the graded paper. The written request must explain in detail what you want the grader to do and where you believe he has made a mistake in grading. Only the instructor will accept these requests.

Academic honesty: All students admitted to the University of Florida have signed a statement of academic honesty committing them to be honest in all academic work and understanding that failure to comply with this commitment will result in disciplinary action. This statement is a reminder to uphold your obligation as a student at the University of Florida and to be honest in all work submitted and exams taken in this class and all others.