Course:CPSC522/January2023

January/February and March Assignments

In January/February you can do one of the following (and you will do the other in March):

Describe some research that has been published. You should choose two papers, by different authors (no authors in common) where one builds on the other. You should describe the background, and then describe the incremental contribution of one paper over the other. What was the actual contribution of the latter paper? The reader should be able to understand the problem, where it fits into the big picture, the solution proposed and how that solution was evaluated. Add your own thoughts on how successful it was and how it can be improved. See http://www.cs.ubc.ca/~poole/cs522/2023/readings.html for some suggested topics.
Foundations: write a foundational page. This can either be a new page on a new topic, or you can replace an existing topic, if you don't like it. If you replace an existing page you need to create an archive of it, so that the reviewers can judge whether it is an improvement. (I suggest that you start doing the first topic (choosing two papers), and if you find some background that should be covered to understand the papers, write a page on it (or one of the topics, if there are multiple topics in your background).

Some topics of particular interest:

graph neural networks
convolutional graph neural networks
knowledge graphs
canonical representation of conditional probabilities / gradient boosted trees
score-based learning of Bayesian network structure (to complement existing page)
deep reinforcement learning
transportability (external validity)
expectation maximization

You need to follow the rules on the main page and you should follow the guidelines there.
Each page should have a principle author. You do not need co-authors but can have co-authors; co-authorship is encouraged. If others help you with your page, you should help them too.
You need to add your page to the table of contents in a position that makes sense. Fell free to edit and change the structure of the table of content to give it a coherent structure.
Please choose a topic that is different from other courses that you have done (or else you need to negotiate with the instructors to make sure you are not counting the same work multiple times).
You should reference (link) to wiki pages and to other research papers as appropriate. It should be clear what the two papers you are describing, but you should also refer to other papers.
The rules are editable and can be changed.

January 20 (or before!) - choose page(s) and start writing
Feb 8 - First draft of page ready for critiquing.
Feb 13 - Critiques due
Feb 15 - Final pages ready for marking
Feb 21. Marking Completed. You need to mark every page (including your own). Use the template at http://cs.ubc.ca/~poole/cs522/2023/project_eval.py

February 27 (or before!) - choose page(s) and start writing
Mar 15 - First draft ready for critiquing.
Mar 17- Critiques due
Mar 19- Final pages reading for marking
Mar 24 - Marking completed. You need to mark every page (including your own). Use the template at http://cs.ubc.ca/~poole/cs522/2023/project_eval.py

Here are some things to think about when grading. Feel free to add questions, and edit the questions if they do not make sense.

Comment on any of the following:

The topic is relevant for the course.
The writing is clear and the English is good.
The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds).
The formalism (definitions, mathematics) was well chosen to make the page easier to understand.
The abstract is a concise and clear summary.
There were appropriate (original) examples that helped make the topic clear.
There was appropriate use of (pseudo-) code.
It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic).
It is correct.
It was too short for the topic
It was an appropriate unit for a page (it shouldn't be split into different topics or merged with another page).
It links to appropriate other pages in the wiki.
The references and links to external pages are well chosen.
I would recommend this page to someone who wanted to find out about the topic.
This page should be highlighted as an exemplary page for others to emulate.

If I was grading it out of 20, I would give it: