## BIOE 498/598 PJ: Spring 2022

Experiment Design & Optimization

#### Course Materials

- Syllabus
**Suggested Textbooks***Design and Analysis of Experiments with R*by Lawson*R for Data Science*by Wickham and Grolemund*Linear Algebra: Foundations of Machine Learning*(BIOE 210 course website)*Surrogates*by Gramacy*Reinforcement Learning: An Introduction*by Sutton and Barto

**R Resources**- RStudio: Open Source Desktop Edition
- R Cheat Sheet

**Assignments**- Homework Submission Guide
- Homework 1 due
**Monday, 2/28 by 5pm**. - Homework 2 due
**Monday, 2/28 by 5pm**. - Homework 3 due
**Friday, 4/29 by 5pm**. - Homework 4 due
**Wednesday, 5/4 by 5pm**.- The AlphaGo documentary is available here.

- Homework 5 due
**Friday, 5/13 by 5pm**.

#### Schedule

- W 1/19: Introduction [slides]
- F 1/21: The R Programming Language [slides] [Rmd]
- M 1/24: Factorial Designs 1: Main Effects [notes]
- W 1/26: Factorial Designs 2: Interactions [continued]
- F 1/28: Factorial Effects with Linear Models [slides][Rmd]
- M 1/31: Identifying Active Effects [slides] [Rmd]
- W 2/2:
*no class* - F 2/4: Fractional Factorial Designs 1 [slides] [Rmd]
- M 2/7:
*no class* - W 2/9: Fractional Factorial Designs 2 [slides] [Rmd]
- F 2/11: Fractional Factorial Designs 3 [slides] [Rmd]
- M 2/14: Replication [slides] [Rmd]
- W 2/16: Designs to Study Dispersion [slides] [Rmd]
- F 2/18: Nominal-the-Best Optimization [slides] [Rmd]
- M 2/21: Screening Designs I [slides] [Rmd]
- W 2/23: Screening Designs II [slides] [Rmd]
- F 2/25: Screening Designs III
- M 2/28: Exam Review [Exam 1 topics]
- W 3/2:
**Exam 1**- Exam Corrections due 3/11 before 5pm.

- F 3/4: Steepest Ascent [slides]
- M 3/7: RSM I: Curvature [slides]
- W 3/9: RSM II: CCDs [slides]
- F 3/11: RSM III: Optimization [slides]
- M 3/14 - F 3/18:
*Spring Break* - M 3/21: RSM IV: Alternative Designs [slides]
- W 3/23: RSM V: The
*rsm*Package (**online lecture**) [Rmd] - F 3/25: RSM VI: Applications
- M 3/28: Class presentations
- W 3/30: Surrogates 1: Space Filling Designs [slides] [Rmd]
- F 4/1: Surrogates 2: Gaussian Process Regression [slides] [Rmd]
- M 4/4: Surrogates 3: Sequential Optimization [slides] [Rmd]
- W 4/6: Surrogates 4: Hyperparameter Tuning [slides] [Rmd]
- F 4/8:
*No class for EOH.* - M 4/11: Surrogates 5: Expected Improvement [slides] [Rmd]
- W 4/13: Homework 3 Workshop
- F 4/15: RL and MDPs [slides]
- M 4/18: Value Functions [slides]
- W 4/20: Rollout [slides]
- F 4/22: Applications: Deep Phenotyping
- M 4/25: Exam Review [Exam 2 topics]
- W 4/27:
**Exam 2** - F 4/29: Discounting and Q-factors [slides]
- M 5/2: Q-learning [slides]
- W 5/4: Summary [slides]