ASRM 499 Section UDL (undergraduate; CRN 77131) and ASRM 595 GDL (graduate; CRN 78325)
- Instructor: Richard Sowers <email@example.com>
- Home page: https://publish.illinois.edu/r-sowers/ (this syllabus can be found there).
- Class meets: 09:30AM – 10:50AM TR in 1068 Lincoln Hall
- Office Hours: Mondays 09:30AM – 10:30AM on Zoom (link available at Canvas)
- Text: Course Notes
- Learning Management System: Canvas
The goal of this class is to understand some basic ideas of deep neural networks. We will understand how they work and apply them to sample datasets.
- Linear Regression
- Logistic Regression
- Elementary Logic
- Gradient Descent
- Feedforward Networks
- Testing, Validation and Training
- Advanced architectures: some combination of
- Recurrent Neural Networks (including LSTM’s)
- Reinforcement Learning
Grading policy: Final grades will be determined on the basis
of the total numerical score (and will be curved).
|Hourly Exam (10/3)||15% of grade|
|Hourly Exam (11/14)||15% of grade|
|Homework||55% of grade|
|Final Project||15% of grade|
Extra credit may be available.
- We will extensively use Google Drive and Google Colab and for teaching material and submission of coding projects. To get access to these, you need to have Account Status “On” for Google Apps at https://cloud-dashboard.illinois.edu/cbdash/ and then log in via g.illinois.edu
- Group coding assignment should be submitted via URL to a Google Colab notebook.
- Groups will be assigned by instructor.
- All date-times will be in Champaign-Urbana
- All students are expected to abide by the Honor Code; you are here to learn (and my interest is in helping you do that).
- Disability requests should be routed through DRES <firstname.lastname@example.org>
- Students who have suppressed their directory information pursuant to the Family Educational Rights and Privacy Act (FERPA) should self-identify to the instructor
- Safety information: http://police.illinois.edu/emergency-preparedness/run-hide-fight/resources-for-instructors/
- The technology of the course may evolve as the semester progresses and as I learn new tools. The content and goals will stay the same.