You should begin working on assignments as soon as they are released. While we've split assignments into more bite sized pieces compared to last semester, most are still quite a bit of work. In particular, do not wait until week 2 to start assignments 0 or 1!
TL;DR: Start early!
Each assignment is due at 11:59pm Pacific on Sundays, unless otherwise stated.
The work you submit must be your own. You are permitted to discuss the assignment at a high level with other students, but you should not share code, implementation details, or specific solutions.
More specifically:
- You may collaborate verbally with other students, but you should not look at or help debug each other's code.
- You can get help on general programming issues, but only in a very general capacity that does not relate to a specific part of the assignment. (example: "Oh, I had issues with that function crashing, but updating TensorFlow to 1.14 fixed it for me.") If in doubt, ask in a private question on Piazza.
- You should not search for or use solutions to the assignment problems that you
find on the web. If you inadvertently come across such a solution, you
must cite it appropriately in your answer. (Bad search: "how to implement
GloVe in TensorFlow". Good search: "how to use
tf.variable_scope" or "how to concatenate matrices") - You should not use external libraries to shortcut parts of the assignment. The
libraries imported in the starter code should be more than sufficient,
although you're welcome to use standard Python libraries like
pdboritertoolsif you desire.
Please do your work in a git repository; you can simply clone the course repo
to get started. If there are any updates or fixes to the assignment, we'll
update the master repo and you can patch your client with git pull. Be sure
to use the assignment submit script (see Assignment 0 for instructions) to submit.
Do not make pull requests on the course repo!
Be sure to git commit often to save your work!