CBE:5120
CBE:5120
Data Science in Chemical and Engineering Systems
[ICON] [GETTING STARTED] [LECTURES] [ASSIGNMENTS] [RESOURCES]
Course Description:
Theory and application of numerical methods and data-driven algorithms towards understanding chemical processes; Scientific computing in the Python programming language; Numerical solutions to differential equations; Nonlinear and constrained optimization; data preprocessing and visualization; dimensionality reduction and clustering; supervised machine learning.
Prerequisites:
At least Senior-level standing in the College of Engineering.
Lectures:
Time: 1:30P-2:30P MWF Place: 3231 SC and/or Zoom
Instructor:
Name: Dr. Joe Gomes
Office: 4110 SC
Email: joe-gomes@uiowa.edu
Office Hours: 3:20P-5:20P F via Zoom
Course Learning Goals:
-
By the end of the course, the student will understand and be able to apply the Python programming language towards performing mathematical and numerical computation.
-
By the end of the course, the student will understand and be able to apply mathematical techniques from linear algebra, differential equations, and optimization towards engineering problems.
-
By the end of the course, the student will understand and be able to apply computational techniques such as data preprocessing and visualization, dimensionality reduction and clustering, and supervised machine learning towards the data-driven modeling of chemical and engineering systems.
-
By the end of the course, the student will have had opportunities to further his or her professional development through practicing written, oral, and graphical communication skills.
Text:
- John Kitchin, Python3 Computations in Science and Engineering, 2018.
- Christopher M. Bishop, Pattern Recognition and Machine Learning, 2009.
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, 2016.
Website:
- ICON: The course ICON site will contain the course calendar, announcements, and grade reports.
- GITHUB: The course GITHUB site will contain class notes and assignments.
Course Calendar:
| Week | Mon | Tue | Wed | Thu | Fri |
|---|---|---|---|---|---|
| Aug | 24 | 25 | 26 | 27 | 28 |
| 1 | First day of class | Introduction to Python | Introduction to Python | ||
| Aug/Sep | 31 | 1 | 2 | 3 | 4 |
| 2 | Introduction to NumPy | Curve Fitting | Kitchin Ch.3 Numerical Integration |
||
| Sep | 7 | 8 | 9 | 10 | 11 |
| 3 | Labor Day No class |
Kitchin Ch.4 Linear algebra |
Kitchin Ch.4 Linear algebra |
||
| Sep | 14 | 15 | 16 | 17 | 18 |
| 4 | Kitchin Ch.5 Solving nonlinear equations |
Kitchin Ch.5 Solving nonlinear equations |
Kitchin Ch.6 Statistics |
||
| Sep | 21 | 22 | 23 | 24 | 25 |
| 5 | Kitchin Ch.6 Statistics |
Kitchin Ch.7 Data analysis |
Kitchin Ch.7 Data analysis |
||
| Sep/Oct | 28 | 29 | 30 | 1 | 2 |
| 6 | Review | Kitchin Ch.8 Interpolation |
Kitchin Ch.9 Optimization |
||
| Oct | 5 | 6 | 7 | 8 | 9 |
| 7 | Kitchin Ch.9 Optimization |
Review | Kitchin Ch.10 Differential Equations |
||
| Oct | 12 | 13 | 14 | 15 | 16 |
| 8 | Kitchin Ch.10 Differential Equations |
Kitchin Ch.10 Differential Equations |
Review | ||
| Oct | 19 | 20 | 21 | 22 | 23 |
| 9 | Review | Kitchin Ch.11 Data Visualization |
Kitchin Ch.11 Data Visualization |
||
| Oct | 26 | 27 | 28 | 29 | 30 |
| 10 | TBD Probabilities and distributions |
TBD Probabilities and distributions |
DL Ch.5 Machine Learning Basics I |
||
| Nov | 2 | 3 | 4 | 5 | 6 |
| 11 | DL Ch.5 Machine Learning Basics II |
Feature Engineering | Ensemble Models | ||
| Nov | 9 | 10 | 11 | 12 | 13 |
| 12 | PRML Ch.6 Kernel Methods |
Clustering | DL Ch.6 FFNN |
||
| Nov | 16 | 17 | 18 | 19 | 20 |
| 13 | Review | DL Ch.7&8 Deep Learning Basics I |
DL Ch.7&8 Deep Learning Basics II |
||
| Nov | 23 | 24 | 25 | 26 | 27 |
| —– | Thanksgiving Break | —– | |||
| Nov/Dec | 30 | 1 | 2 | 3 | 4 |
| 14 | DL Ch.7&8 Deep Learning Basics II |
DL Ch.9 Convolutional Networks |
DL Ch.9 Convolutional Networks |
||
| Dec | 7 | 8 | 9 | 10 | 11 |
| 15 | DL Ch.10 Recurrent Networks |
Final Project Presentations | —– | ||
| Dec | 14 | 15 | 16 | 17 | 18 |
| —– | Finals Week | —– |