Re:No physics? No problem. AI weather forecasting is already...
by PaulDavisThe1st on Tuesday June 04, 2024 @05:07PM
(#40578952)
> To train a NN you need a training set of data, that data follows a certain order or pattern that represents the model that the person has
I have been repeatedly assured by people who manage to sound authoritative about NN's and ML here on HN that, despite my instincts to the contrary, this claim is no longer true. I continue to doubt it, but there you have it.
Your claims about language are quite interesting, and quite controversial.
Re:No physics? No problem. AI weather forecasting is already...
by nico on Tuesday June 04, 2024 @06:10PM
(#40579475)
Ok, let’s say you don’t need data
What is the goal of that NN? How are inputs and output of that NN defined?
If you define any structure or properties of the NN, or any description at all, you are implicitly creating a model. Any NN is already a model
Not sure why that would be controversial
Re:No physics? No problem. AI weather forecasting is already...
by PaulDavisThe1st on Wednesday June 05, 2024 @10:25AM
(#40585176)
No, you obviously need data. But several times when I've challenged the unacknowledged role that data pre-identification and classification is playing, I've been told that this isn't needed any more. You can just throw unorganized, unclassified data at these things (so they claim), and it will "figure it out".
To train a NN you need a training set of data, that data follows a certain order or pattern that represents the model that the person has
As long as the NN behaves as expected by the person setting it up, then it is useful as a model
How useful? That depends on what you are trying to do, your model and the data
If you want to take it to its extreme, all language is a model. Even what I’m expressing right now with this text. It’s just a model of what I’m thinking and the meanings I’m trying to convey