News for hackers. Stuff that matters.
Re:Paradigms of A.I. Programming: Case Studies in Common Lis... by codr7 on Friday May 05, 2023 @06:48AM (#35827567)
Compared to any other approach to AI we've come up with, neural networks are way more complicated.

Besides, they're not the final solution to anything.

Learning your history is the only way to avoid repeating the same mistakes.

Re:Paradigms of A.I. Programming: Case Studies in Common Lis... by jstx1 on Friday May 05, 2023 @07:08AM (#35827704)
You should really know that there's more to ML than neural networks. Those are the simpler approaches I was referring to (like linear models, ensemble models etc). They are

1. Machine learning.

2. Not neural networks.

3. Not in Norvig's book.

4. Still useful and relevant.

Re:Paradigms of A.I. Programming: Case Studies in Common Lis... by lukego on Friday May 05, 2023 @08:46AM (#35828513)
In fairness they are almost certainly in Norvig's other book...
Re:Paradigms of A.I. Programming: Case Studies in Common Lis... by codr7 on Friday May 05, 2023 @08:47AM (#35828527)
TIL; can't remember ever hearing about them before, where are they used?

But it seems like we finally agree on something, simpler approaches to AI that predate neural networks are still potentially useful.

Because you're not going to claim that ML is the only useful kind of AI, are you?