The problem with training isn’t purposely creating things that pass. It’s purposely creating things that don’t. In order to figure out what doesn’t pass, we need a predicate function. Once we’ve figured out how to find things that won’t pass, we’ve already found the answer.
I claim a rock is a non-person. I expect you accept that statement, I expect that you therefore have a non-person predicate function, yet I also expect you haven’t found the answer.
I accept that in order to classify something, we need to be able to classify it.
I’m suggesting there might be a function that classifies some things incorrectly, and is still useful.
The problem with training isn’t purposely creating things that pass. It’s purposely creating things that don’t. In order to figure out what doesn’t pass, we need a predicate function. Once we’ve figured out how to find things that won’t pass, we’ve already found the answer.
Doesn’t follow. Consider;
I accept that in order to classify something, we need to be able to classify it.
I’m suggesting there might be a function that classifies some things incorrectly, and is still useful.