The most important thing is to be able to run a lot of experiments! A list of useful things to do before the second lecture includes:

• make sure you can spin up a GPU server, that you can shut it down when it is finished
• run the code shown in the lecture
• use the documentation, use the doc function inside juypter notebook
• do some searching of the fast.ai docs
• see if you can grab the fast.ai documentation notebooks and try running them
• read a chapter of the fast.ai book
• do the questinnaire at the end of the chapter (not everything has been covered yet, answer only the questions that you can)
• try to get comfortable with running code