this post was submitted on 23 Aug 2024

73 points (95.1% liked)

Machine Learning

499 readers

1 users here now

A community for posting things related to machine learning

Icon base by Lorc under CC BY 3.0 with modifications to add a gradient

founded 2 years ago

MODERATORS

73

What’s Really Going On in Machine Learning? Some Minimal Models | Stephen Wolfram | August 22, 2024 (writings.stephenwolfram.com)

submitted 4 months ago by ericjmorey to c/machine_learning

23 comments fedilink hide all child comments

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

[–] GetOffMyLan 6 points 4 months ago* (last edited 4 months ago) (1 children)

More data doesn't mean more processing.

They have a fixed number of interconnected nodes that encode the data via the weights between them.

So processing requirements are the same. Training is where a lot of power goes though.

This also gives it the ability to solve things we don't have an equation for. As long as we know the input and output we can train an NN to do the calculations even if we don't know the equation ourselves.

The black box nature is a problem but that's also where it's power comes from.

[–] [email protected] 2 points 4 months ago

I see what you mean. I made a comment further down as a response to someone else where I go into more detail about my train of thought where I explain more of the issues I've found with this type of machine learning.