CS 342 - Neural networks - Fall 2021
meets TTH 9:30am-11am in GDC 2.216 (zoom mirror; see canvas)
Class will be in-person with a live Zoom mirror. Office hours will be exclusively through Zoom. For all Zoom links, see the Zoom tab in Canvas.
If you’d like to meet outside of office hours, please email.
|Name (email)||Office Hours|
|Instructor||Philipp Krähenbühl ( philkr (at) utexas.edu)||Th 11am-12pm|
|TA||Jeffrey Zhang ( jozhang (at) utexas.edu)||T 12pm-1pm|
|TA||Tianjian Meng ( mengtianjian (at) utexas.edu)||W 4pm-5pm|
|TA||Jierui Lin ( jerrylin (at) utexas.edu)||Th 4pm-5pm|
|TA||Tianwei Yin ( yintianwei (at) utexas.edu)||T 5pm-6pm|
This course covers the basic building blocks and intuitions behind designing, training, tuning, and monitoring of deep networks. We will cover both the theory of deep learning, as well as hands-on implementation sessions in pytorch. We will also cover a series of application areas of deep networks in: computer vision, sequence modeling in natural language processing, deep reinforcement learning, generative modeling, and adversarial learning. In the homework assignments, we will develop a vision system for a racing simulator, SuperTuxKart, from scratch.
Prerequisites: Python, basic ML background
The schedule below shows the due dates for all modules. Open problems are optional.
Each week, we start with a quiz on the course material Tuesday, and then work through the results of the quiz and any questions in class. In the second half of class, we start on a medium sized coding project related to the course material. We’ll split the class into even groups, and each group will solve the problem individually. We’ll train any larger networks over night following the class, and then compare solutions.
The class will be in-person, until disaster strikes. However, there is a live zoom link for anybody that is uncomfortable with an in-person setting. We wont record the zoom sessions.
Either in-person or zoom attendance is required. You may miss up to 3 classes without any excuse. We use an instapoll for attendance (please bring a phone or laptop).
Please join us over zoom if you have any health concerns, or may be sick.
|Thu||Aug 26||Introduction||intro colab|
|Sun||Aug 29||Up to and including Background.Summary|
|Tue||Aug 31||Coding - K-Nearest Neighbors||colab|
|Thu||Sep 02||Coding - Part II|
|Sun||Sep 05||Up to and including First example.Summary|
|Tue||Sep 07||Coding - Linear Classifier||colab|
|Thu||Sep 09||Coding - Part II|
|Sun||Sep 12||Up to and including Deep networks.Summary|
|Tue||Sep 14||Coding - MLP||colab|
|Thu||Sep 16||Coding - Part II|
|Sun||Sep 19||Homework 1 due 11:59pm|
|Sun||Sep 19||Up to and including Convolutional Networks.Building efficient convolutional networks|
|Tue||Sep 21||Coding - CNN||colab|
|Thu||Sep 23||Coding - Part II|
|Sun||Sep 26||Up to and including Making it work.Initialization in pytorch|
|Tue||Sep 28||Coding - CNN Blocks||colab|
|Thu||Sep 30||Coding - Part II|
|Sun||Oct 03||Homework 2 due 11:59pm|
|Sun||Oct 03||Up to and including Making it work.Open Problem: Pruning and compression|
|Tue||Oct 05||Coding - Image Generation||colab|
|Thu||Oct 07||Coding - Part II|
|Sun||Oct 10||Up to and including Making it work.Summary, a practical guide to deep network optimization|
|Tue||Oct 12||Coding - Binary Segmentation||colab / in class colab|
|Thu||Oct 14||Coding - Part II|
|Sun||Oct 17||Homework 3 due 11:59pm|
|Sun||Oct 17||Up to and including Computer Vision.Case Study: RetinaNet|
|Tue||Oct 19||Coding - Keypoint Estimation||colab|
|Thu||Oct 21||Coding - Part II|
|Sun||Oct 24||Up to and including Computer Vision.Summary|
|Tue||Oct 26||Coding - Keypoints Continued||colab|
|Thu||Oct 28||Coding - Part II|
|Sun||Oct 31||Homework 4 due 11:59pm|
|Sun||Oct 31||Up to and including Reinforcement learning.Gradient free optimization|
|Tue||Nov 02||Coding - Imitation Learning||colab|
|Thu||Nov 04||Coding - Part II||in-class colab|
|Sun||Nov 07||Up to and including Sequence modeling.Summary|
|Tue||Nov 09||Coding - Imitation Learning Continued.||colab|
|Thu||Nov 11||Coding - Part II|
|Sun||Nov 14||Homework 5 due 11:59pm|
|Sun||Nov 14||Up to and including Embedding learning.Summary|
|Tue||Nov 16||Coding - Part I||colab|
|Thu||Nov 18||Coding - Part II|
|Sun||Nov 21||Up to and including Adversarial attacks.Summary|
|Tue||Nov 23||Philipp research presentation|
|Thu||Nov 25||No class - Thanksgiving|
|Sun||Nov 28||Up to and including Final words.Open Problem: Bias, fairness, and ethics in deep learning|
|Tue||Nov 30||Final project presentations I|
|Thu||Dec 02||Final project presentations II|
|Sun||Dec 05||Makeup Homework due 11:59pm|
|Sun||Dec 05||Final project due 11:59pm|
Assignments and final project
- homework 1 (10%)
- homework 2 (10%)
- homework 3 (10%)
- homework 4 (10%)
- homework 5 (10%)
- homework 6 (make up homework; may replace any above)
- final project (30%)
All homework are due at 11:59pm, but you’ll have one additional hour to upload your assignment to canvas (in case your internet connection is really slow). Please do not email me for further extensions.
Collaboration / Academic Honesty Policy
Collaboration is not allowed for homework or Quizzes. Every homework and quiz needs to be solved individually. We will check for duplicates. For the final project groups of up to 4 students are allows. Different groups are allowed to discuss ideas and share data, but no code.
The online course format allows for multiple methods of identity verification, collusion, collaboration and plagiarism monitoring and detection. A violation of the course policy may include (but is not limited to) the following:
- Providing your UT EID to any other person
- Collaborating or sharing information with another person regarding the material on any quiz, assessment or assignment, before, during and/or after any quiz, assessment or assignment
- Recording any quiz, assessment or assignment material in any format
- Failing to properly cite language, ideas, data, or arguments that are not originally yours
- The public (such that it can be viewed by more than one person) posting of any form of a test bank or group of questions from any assignment
- Consulting forbidden materials or sources of information
The University of Texas at Austin Academic Integrity principles call for students to avoid engaging in any form of academic dishonesty on behalf of yourself or another student. Grade-related penalties are routinely assessed (“F” in the course is not uncommon), but students can also be suspended or even permanently expelled from the University for scholastic dishonesty.
If you have any questions about what constitutes academic dishonesty, please refer to the Dean of Students website or contact the instructor for this course.
You must agree to abide by the Honor Code of the University of Texas. You will not work with or collaborate with others in any way while completing any of the graded course assignments.
- 1 day: -25%
- 2 days: -50%
- 3 days: -100%
- 1 day: - 100%
You have a total of 3 slip-days for your homework. There are no slip-days for the final project or quizzes. A homework that is 3 days late will be graded at -100% irrespective of slip-days, as we will release the solution on day 3. Slip-days are applies greedily (automatically).
Assignments, Assessment, Evaluation
- Quizzes (10%): Quizzes (linear, may miss 2).
- Coding (10%): Attendance and involvement (may miss 3).
- Homework (50%): There are six homework assignments in this class (10% per assignment; lowest score is dropped).
- Final Project (30%): There is one final project in this class.
Documented Disability Statement
The University of Texas at Austin guarantees that students with disabilities have access to appropriate accommodations. You may request an accommodation letter from the Division of Diversity and Community Engagement, Services for Students with Disabilities https://diversity.utexas.edu/disability/.
If you have approved accommodations for the course, please contact us to arrange them. Please do this as soon as possible, so that you can have the benefit of the accommodations throughout the duration of the course.
We expect that you will treat online discussions as though you are having a civil, respectful discussion with your fellow classmates in the same classroom. Please refrain from using profanity or any euphemisms for profanity. Please do not bait other commenters or personally attack them. Please do not use sarcasm in a way that can be misinterpreted negatively. And please do not make the same point over and over again. In short, please just respect the right of your colleagues to ask questions and discuss their opinions about the subject matter of our course on the discussion board. Violators of these discussion rules will simply be shut out from all class communications—email, Piazza, and office hours.
Behavior Concerns Advice Line
If you are worried about someone who is acting differently, you may use the Behavior Concerns Advice Line to discuss by phone your concerns about another individuals behavior. This service is provided through a partnership among the Office of the Dean of Students, the Counseling and Mental Health Center (CMHC), the Employee Assistance Program (EAP), and The University of Texas Police Department (UTPD). Call 512-232-5050 or visit https://besafe.utexas.edu/behavior-concerns-advice-line
This syllabus is subject to change. Last updated: December 13, 2021