CA-3 + Essay: Advanced Deep Learning (EE6934)

Deadline: April 14, 2023 at 5pm


Read carefully: This is an individual assignment. Academic integrity must be stricly followed. Copying from other's code/text or from anyone or any source is not allowed (unless stated clearly in the instructions). Exchanging codes/text is not allowed. Software will be used to detect any form of source code plagiarism. Your submitted code must be grouped/separated into the same parts in the instructions. In your submission, you must provide us with all necessary libraries, so that we can compile your code. You are not allowed to use any toolboxes unless stated in the instructions explicitly (if you are not sure, you should ask). If you use separate files in your submission, you must zip them to one file. The submission must not be in separate files in different times (it must be submitted together once). The deadline is strict, so please prepare and plan early and carefully. Late submission will cause score deduction (assuming 100 is the full score, there will be deduction of 10 points in the first 24 hours, 30 points in the next 24 hours, 60 points in the next 24 hours, and 100 points beyond this).
Frequently Asked Questions: Q&A

Part 1: Code Implementation

  1. Select a deep learning paper that is published in ICLR, NeurIPS and CVPR from year 2020 to 2023. Note, the paper must be about deep learning.
  2. To avoid two or more students selecting the same paper and also to avoid any papers that are possibly not suitable, you must inform me by email the title of the paper by March 22, 2022, at 5pm with subject: "[EE6934]: Paper".
  3. With respect to the selected paper, find the publicly available code on the internet or implement the paper by yourself. You are allowed to use a publicly available code, however you must state it clearly in the code and also in your report.
  4. Find relevant data beyond the ones used in the paper for the purpose of either training or testing.
  5. Experiment with the code using your own data for testing.
  6. You must submit your code and ensure we can compile the code (hence, you must include relevant libraries).

Part 2: Report

Write a report in PDF using this template: [zip].

  1. Write your report by answering the specific questions available on the provided template. You must keep the questions in your report.
  2. In your report, you are allowed to write anything beyond the questions. However you must make it clear in your report, and must be placed after provided the questions. See the template for details.
  3. The maximum length of the report is 10 pages excluding the references.

Part 3: Video Presentation

  1. Create a video presenting your report with duration of maximum 15 minutes.
  2. In the video, you must use powerpoint to show your slides.
  3. In the video, you must show your face next to your powerpoint slides while you're presenting.
  4. The video must be in the AVI or MP4 format.
  5. The presentation must contain the following information taken from your report:
    • Title of the selected paper
    • Summary
    • Experiments and Analysis
    • Strengths
    • Weaknesses
    • Possible Improvement
* Any recording tool is fine, but you might want to use Zoom to record your presentation.


Submission

Submit your code, report and video via Canvas by the deadline.