Textbooks

The required textbook for this class is (note that the material of the class goes beyond this book):

Grading

The grading breakdown is as follows:

Homework (30%)

There will be three assignments, each account for 10% towards your final score. Each assignment includes written analysis and/or programming for testing your understanding of the taught content.

Late policy:
Assignments are due at 11:59 PM of the due date. You will be allowed 2 total late days (48 hours) without penalty for the entire semester (for homework only, not applicable to exams or projects). Once those days are used, you will be penalized according to the following policy:

  • Homework is worth full credit before the due time.
  • It is worth 75% credit for the next 24 hours.
  • It is worth 50% credit for the second next 24 hours.
  • It is worth zero credit after that.

Follow the Georgia Tech Academic Honor Code.

Regrade Requests:
If you believe that the course staff made an objective error in grading, you may submit a regrade request on Gradescope within 3 days of the grade release. Your request should briefly summarize why the original grading was incorrect. Note that staff may regrade the entire submission, so it is possible for you to lose more points than you gain if a mistake was overlooked in the first time.

You are required to use Latex (OverLeaf Latex Example in the Video), or a word processing software to generate your solutions to the written questions. Handwritten solutions WILL NOT BE ACCEPTED. You can easily export your Jupyter Notebook to a Python file and import that to your desired Python IDE to debug your code for assignments.

Project (40%)

Team Size:
Each project must be completed in a team of 3–5. Once you have formed your group, please send one email per team to the class instructor list with the names of all team members. If you have trouble forming a group, please send us an email and we will help you find project partners.
The team formation email will be due at 11:59 PM on Feb 10th.

Projects Topics:
Reproduce classic papers, include but not limited to:

You may also refer to the Stanford Project Examples.

2 Deliverables:

  • Presentation (15%)
  • Final Report (25%):
    All write-ups should use the NeurIPS style.
    Your final report is expected to be 5 pages excluding references. It should have roughly the following format:
    • Introduction: Problem definition and motivation
    • Background & Related Work: Background info and literature survey
    • Methods:
      • Overview of your proposed method
      • Intuition on why should it be better than the state of the art
      • Details of models and algorithms that you developed
    • Experiments:
      • Description of your testbed and a list of questions your experiments are designed to answer
      • Details of the experiments and results
    • Conclusion: Discussion and future work

The project final report will be due at 11:59 PM on April 28th.

Criteria:

  • 30% for proposed method (soundness and originality)
  • 30% for correctness, completeness, and difficulty of experiments and figures
  • 20% for empirical and theoretical analysis of results and methods
  • 20% for quality of writing (clarity, organization, flow, etc.)

Computing Resources:
Google Colaboratory allows free access to run Jupyter Notebooks using GPU resources. The Google Cloud Platform and AWS Educate are also good resources. The GitHub Student Developer Pack also offers free Microsoft Azure and Digital Ocean credits. This semester, we are also offering PACE ICE, Georgia Tech’s in-home cluster to students.

Exam (30%)

One exam will be held on March 12 in lieu of the regular class:

  • It will be a closed-book exam, so no notes or communication with peers is allowed.
  • There will be no make-up exams, so be sure to attend on the scheduled date. Missing the exam will result in zero credit.

Participation (5% extra credit)

We appreciate student participation in the class! We will be awarding, on a case-by-case basis, up to 5% in extra credit to the top Ed contributors based on the number of (meaningful) instructor-endorsed answers or other significant contributions that assist the teaching staff or other students in the course. The most helpful contributor will receive the greatest amount of extra credit, and other students with significant contributions will receive a percentage of that.

AI-Based Assistance

We are using the AI assistant policy developed by David Joyner and shared by other classes at Georgia Tech (CS 7643 Deep Learning). The summary is that you should treat your AI source like a human source, with all accompanying plagiarism implications:

We treat AI-based assistance, such as ChatGPT and Copilot, the same way we treat collaboration with other people: you are welcome to talk about your ideas and work with other people, both inside and outside the class, as well as with AI-based assistants.

However, all work you submit must be your own. You should never include in your assignment anything that was not written directly by you without proper citation (including quotation marks and in-line citation for direct quotes). Including anything you did not write in your assignment without proper citation will be treated as an academic misconduct case. If you are unsure where the line is between collaborating with AI and copying AI, we recommend the following heuristics:

Heuristic 1: Never hit “Copy” within your conversation with an AI assistant. You can copy your own work into your own conversation, but do not copy anything from the conversation back into your assignment. Instead, use your interaction with the AI assistant as a learning experience, then let your assignment reflect your improved understanding.

Heuristic 2: Do not have your assignment and the AI agent open at the same time. Similar to the above, use your conversation with the AI as a learning experience, then close the interaction down, open your assignment, and let your assignment reflect your revised knowledge.

This heuristic includes avoiding using AI directly integrated into your composition environment: just as you should not let a classmate write content or code directly into your submission, so also you should avoid using tools that directly add content to your submission.

Deviating from these heuristics does not automatically qualify as academic misconduct; however, following these heuristics essentially guarantees your collaboration will not cross the line into misconduct.