• 1 Post
  • 139 Comments
Joined 2 years ago
cake
Cake day: June 4th, 2023

help-circle
  • OhNoMoreLemmy@lemmy.mltoMicroblog Memes@lemmy.worldlazy ass
    link
    fedilink
    English
    arrow-up
    1
    ·
    17 hours ago

    I guess it might work if HR don’t know how an LLM works. There’s not many that can edit a word file so it includes whited-out footnotes.

    You’re better off getting a friend to lie for you. They can say they added it while helping you with formatting and you know nothing about it.









  • In practice it’s very systematic for small networks. You perform a search over a range of values until you find what works. We know the optimisation gets harder the deeper a network is so you probably won’t go over 3 hidden layers on tabular data (although if you really care about performance on tabular data you would use something that wasn’t a neural network).

    But yes, fundamentally, it’s arbitrary. For each dataset a different architecture might work better, and no one has a good strategy for picking it.


  • Probably because there’s no good reason.

    At least one intermediate layer is needed to make it expressive enough to fit any data, but if you make it wide enough (increasing the blobs) you don’t need more layers.

    At that point you then start tuning it /adjusting the number of layers and how wide they are until it works well on data it’s not seen before.

    At the end, you’re just like “huh I guess two hidden layers with a width of 6 was enough.”




  • It’s interesting. There’s a lot of talk about how chatgpt makes people lazy, but honestly I think Google killed the “read the manual” ethos.

    Back in the day when you couldn’t just search for everything, you needed enough understanding of the manual to find anything in the index.

    So a key part of figuring anything out was reading at least the start of the manual.

    Now, fuck it, you just type into Google and try to guess enough context to understand what’s going on.