A few months ago I came across maximum mean discrepancy as a measure of distribution difference, and today I read this term and totally forgot what is means and had to find a youtube video to refresh my understanding. This happens a lot of times in my research. I feel like unless something is really basic (e.g. CNN, cross entropy, etc) and used a lot in my day-to-day model building, I easily forgot what I have read. I wonder is it just because I have a bad memory or I do not have a good way to organize information?
I have an overleaf doc of papers I like/are useful. It is linked so I can quickly access each paper.
do you read it e.g. every few days, to refresh your memory? Or just use it as reference? If it is latter, how does it compare with direct Google search?
I use it as reference. It’s much better than google search, because in each section I include only important details from each paper (not the full thing). This lets me quickly remember important stuff about each paper as well as how it connects to relevant work