Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 10 months ago

MODERATORS

communick@academy.garden

[D] how do you remember methods in papers you read? (alien.top)

submitted 10 months ago by Illustrious-Pay-7516@alien.top to c/machinelearning@academy.garden

28 comments fedilink hide all child comments

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?

you are viewing a single comment's thread
view the rest of the comments

[–] Zemeniite@alien.top 1 points 10 months ago (1 children)

Honestly, this makes me sad. I completely agree with you and experience this myself but it is disheartening.

I’m currently way too overworked to do this but I have had the idea of making a personal wiki. Read a paper those bazillion times I need until I understand it (some great papers are truly poorly written) and make succinct notes (definitions, math, code, conclusions, usage cases). Then use the wiki whenever I forget something.

I don’t know what platform / tool to use for the wiki because I don’t want to be forever required to pay for a subscription fee yet I want it accessible from multiple devices and have a nice search.

[–] Seankala@alien.top 1 points 10 months ago (1 children)

Don't be sad, it's just a part of how things are you just have to choose a method and stick to it.

I personally use Notion. I've created a database and added properties like date, venue, authors, organizations, etc.

For example, the other day I needed to recap what the BLIP paper was about so I just searched the paper in the database and took a look at the page. On that page I've highlighted different text with different colors depending on when I came back to read it.

Took me a while to get this working and into the habit of it though.

[–] Zemeniite@alien.top 1 points 10 months ago (1 children)

I’ve been in the industry for 5 years. I don’t know how many papers I have read but I know that I recall only few. I regret not writing things down earlier but I never have the time. Ugh, I just need to swallow this up and start to do this

[–] Seankala@alien.top 1 points 10 months ago (1 children)

Well I don't know your situation but I feel like the "never have time" excuse may not necessarily be true. Even creating a page in Notion and writing down one line is enough for me. I feel like what was holding me back before was the trap of perfectionism. I wouldn't want to write anything unless I could make it into some conference-poster-quality page.

[–] Zemeniite@alien.top 1 points 10 months ago

It probably isn’t, perfectionism does sound more like it. Thanks!