Hey everyone,
There are so many tiny tidbits of information we get from the course and many other lectures in deep learning. I decided to compile them into a handy guide (or a checklist of sorts)
I tried to cover (almost) all the tricks Jeremy mentioned across the past 3 iterations of the course along with others that I found helpful over the past few years. With respect to choosing hyper params, identifying aspects which make your model behave weirdly, debugging and much more.
Would absolutely love to hear your feedback on the same 
Hope it helps someone!!
(Also note that I don’t get monetized for any of this and I just thought it would be helpful for someone who is facing the same challenges as I did)
Hope you have a wonderful day and stay safe!