IE 534 and CS 547 (Deep Learning)
Section D
CRN 72857 and 72858
- Instructor: Richard Sowers <r-sowers@illinois.edu>
- Home page: https://publish.illinois.edu/r-sowers/ (this syllabus can be found there).
- TA’s: XXX <XXX@illinois.edu>, XXX <XXX@illinois.edu>
- Class meets: 08:00AM – 09:20AM TR on Zoom (see Piazza)
- Text: Deep Learning, Goodfellow, Bengio, and Courville
- Logistics: Piazza
- Safety information: http://police.illinois.edu/emergency-preparedness/run-hide-fight/resources-for-instructors/
- Videos are archived as playlists on Illini Media Space:
Topics:
- Linear Regression (Week 1)
- Logistic Regression (Week 2)
- Elementary Logic
- Backpropagation
- Stochastic Gradient Descent
- Testing, Validation and Training
- Feedforward Neural Networks
- Recurrent Neural Networks
- LSTM Networks
- CNN’s
- Reinforcement Learning
Grading policy: Final grades will be determined on the basis
of the total numerical score (and will be curved).
of the total numerical score (and will be curved).
Component | Weight | |
Hourly Exam (3/16) | 15% of grade | |
Hourly Exam (5/4) | 15% of grade | |
Quizzes, Projects, Homework | 70% of grade |
Logistical notes:
-
- Asynchronous notes will be made available on a module-by-module basis
- We will observe the Spring 2021 semester non-instructional days: Wed-February 17th, Wed-March 24th, Tues-April 13th
- Some homework assignments will be on BlueWaters. Extra credit may be assigned for early submission (BlueWaters is a shared resource, and may intermittently bottlenecked)
- Random subsets of individual assigments will be graded.
- There will be a number of assignments involving data (and coding). Python (and Jupyter notebooks) will be the preferred framework for this (Python is one of the top languages for data analysis, so this is designed to be to your benefit). NB: Anaconda is one of the common distributions of Python.
- 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
- Coding HW must be submitted by sending the TA’s a link to a Google Colab notebook (and giving the TA’s viewing permission).
- Many assignments will be group projects, with 4 people being the optimum group number. A “Groupness extra credit” will be added to each assignment, with the value of
- 3 if your group has 4 members
- 2 if your group has 3 or 5 members
- 1 if your group has 2 members
- 0 in all other circumstances.
- 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 <disability@uiuc.edu>
- Students who have suppressed their directory information pursuant to the Family Educational Rights and Privacy Act (FERPA) should self-identify to the instructor
- 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.