Here’s a list of frequently asked questions (FAQ). If you have any questions that you think somebody else might have already asked, go through the list, and maybe you will find an answer here.
A: Submit your "solutions to the theory part", the "report" and the "code" for the programming part to Gradescope, separately.
A: Conventionally, that means “apply the function elementwise”. Same thing applies to activation functions (such as logistic sigmoid).
A: Generally we will closely follow the assignment policy: no extension for the theory part & 4-day prorated penalty for the programming part. Contact one of the TAs or the lecturer for special cases.
A: Yes, otherwise a penalty will be imposed.
A: Unless it is specified, no.
A: It is very hard (impossible actually) to find a time that did not conflict somewhat for someone. We're sorry for the conflict, and we're also available on Piazza to answer questions. Feel free to ping the TAs if you want to schedule a meeting other than the official office hours.
A: Unless it is specified, you can and are encouraged to use mini-batch.
A: You are only allowed to use PyTorch (except when it's specified otherwise).