CPSC 320

Today we begin/continue working on a proof that our clustering algorithm is correct.

• Don’t forget this week’s quiz in tutorial!
• For next class, please read 5.1 in the textbook. No pre-class quiz, however.
• Midterm review session with Stephanie and Vaastav on Tue 14 Feb 5-7PM in MCML 166.
• After the extension due to snow, Assignment #2 is due Mon 6 Feb at 10PM. As always, a solution will be available on the course website shortly after the deadline.
• Here are our notes to wrap up photo clustering.

Today we’ll continue (and maybe finish!) our work on an algorithm for clustering photos.

• UPDATE on the last pre-class quiz: A minority of people correctly identified the greedy condition used in Dijkstra’s Algorithm. PLEASE GO BACK AND RE-READ THAT SECTION! If you have trouble with it, ask questions (in class, on Piazza, in office hours, etc.). You do need to learn not only from lecture and tutorial but from the textbook, and Dijkstra’s Algorithm is an example of a very important algorithm we expect you to learn about from the text! (Yes, we can ask about it on the exam.)

  Additionally, participation in online quizzes has been dropping. Remember these are graded, and if you do well on them, they can be 5% of your course grade. If you really want to ignore them, they’ll only be 1%, but (a) you need to do the readings anyway to prepare for the exams, (b) if you don’t do the readings before class, you’ll learn much less in class, and (c) you’ll have to fill in that other 4% with some other course element, which you’ll be doing much worse on if you don’t do the readings. So, do the readings and the pre-class quizzes. See the syllabus for more info on our grades.

• For next time, read Sections 4.7. No pre-class quiz, however.
• In case we get there, here’s a set of notes to wrap up photo clustering.
• There is a third quiz in tutorial next week, but there will be no follow-up assignment. Instead, use the quiz and problems as an opportunity to practice for the exam. (We’ll clarify where the grade for the “assignment” portion of this quiz/assignment comes from soon.)
• The midterm exam is coming up on Wed 15 Feb. We’ll post details about the exam (e.g., length of the individual and group stages and room assignments) on Piazza soon.

Today we’ll continue working on clustering of photos with a graph-based approach.

• Here is a sample solution to our clustering notes.
• For next time, read Sections 4.5-4.6.
• Complete the pre-class quiz before next time (by 10PM on Thu 2 Feb).
• Assignment #2 is due on Friday at 10PM on GradeScope.
• Just for fun: If you’re looking for implementation challenges, make an open-source web-based app for one of the problems below and post a link to the app and the source on Piazza for 1 bonus point (for an individual making a good version) or 2 bonus points per person (for a team making a very good version). (Not sure what web-based system to use or where to write it? I’m enjoying using Meteor on Cloud 9.)
  • The user uploads a set of photos and then drags a slider (or otherwise adjusts the desired number of categories) to see the photos auto-categorized into groups. (Choose and implement some good similarity metric between photos.)
  • A CPSC 320 student uses the app to learn about the random walk definition of a graph node’s PageRank. The app shouldn’t (only?) simulate the random walk for the student, but rather help the student walk through the algorithm for the random walk and understand what results it produces. (We’ve already got some good implementations of the walk itself; so, take it one step further by creating a visualization of some sort.)