Project 1: Face Recognition and Gender Classification with Regression (Worth 10%, Due Jan. 29 at 22:59PM).
Project 1 bonus: Investigating k-NN (A bonus of 1%, Due Feb. 5 at 22:59PM).
Project 2: Deep Neural Networks for Handwritten Digit and Face Recognition (Worth 10%, Due Feb. 23 at 22:59PM).
Project 2 bonus: Visualizing Deep Neural Networks (Worth up to 2%, Due Feb. 26 at 22:59PM).
Project 3: Fake News! (Worth 10%, Due Mar. 19 at 22:59PM).
Project 3 bonus: More Fake News! (Worth 2.5%, Due Mar. 24 at 22:59PM).
Project 4: Tic-Tac-Toe with Policy Gradient (Worth 10%, Due Apr. 2 at 22:59PM).
Project 4 bonus: Tic-Tac-Toe with Self-Play (A bonus of 1%, Due Apr. 4 at 22:59PM).
There will be four projects. The first project is to be done independently, and the rest can be done in pairs. The late penalty is 4% of the possible marks per day, rounded up. Late assignments are accepted for up to three days after the deadline.
Sample Project and Template
Here's a sample report/LaTeX template containing advice on how to write project reports in AI courses: Report Zip, tex file, and pdf output. The example is based on Programming Computer Vision with Python pp27-30.
All project submission will be done electronically, using MarkUs.
For group projects, to submit as a group, one of you needs to "invite" the other to be partners, and then the other student needs to accept the invitation. To invite a partner, navigate to the appropriate Assignment page, find "Group Information", and click on "Invite". You will be prompted for the other student's CDF user name; enter it. To accept an invitation, find "Group Information" on the Assignment page, find the invitation listed there, and click on "Join".Only one student must invite the other!
If both students send an invitation, then neither of you will be able to accept the other's invitation. So make sure to agree beforehand on who will send the invitation! Also, remember that, when working in a group, only one person must submit solutions. Your code should generate all the figures used in the report; describe and analyze the inputs and the outputs; add your interpretation where feasible.