Zemeniite

joined 11 months ago
sorted by: new top controversial old
[D] Do you obsessively watch your models train? in c/machinelearning@academy.garden
[–] Zemeniite@alien.top 1 points 11 months ago

Instead of relying on Weights & Biases sending me an email I’ve implemented alerts being sent to either a Slack or a Discord channel. They are always sent on error with the error message. I also receive a message after a predetermined interval of training with metrics.

Just another idea if someone doesn’t want to rely on W&B

[D] how do you remember methods in papers you read? in c/machinelearning@academy.garden
[–] Zemeniite@alien.top 1 points 11 months ago

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

[D] how do you remember methods in papers you read? in c/machinelearning@academy.garden
[–] Zemeniite@alien.top 1 points 11 months ago (2 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

[D] how do you remember methods in papers you read? in c/machinelearning@academy.garden
[–] Zemeniite@alien.top 1 points 11 months ago (4 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.