News for hackers. Stuff that matters.
Re:The Emergent Symbolic Structure of Artificial Neural Netw... by riceflippa on Wednesday September 02, 2026 @07:04AM (#49534557)
> Is evaluating these closed-form representations more computationally efficient?

No it is way worse since computationally they are same things with symbolic having overhead of attending to the symbols.

Re:The Emergent Symbolic Structure of Artificial Neural Netw... by rwmj on Wednesday September 02, 2026 @07:13AM (#49534624)
Is it though? Brute force searching generally scales like 2^n. LLMs on the other hand can obviously be trained, and even though training is massively resource intensive, it's not 2^n.
Re:The Emergent Symbolic Structure of Artificial Neural Netw... by sigpwned on Wednesday September 02, 2026 @09:23AM (#49535852)
My naive middle-of-the-night Claude question said the same thing. At least for this approach. I have not read the paper closely enough to refute you. But the concept of a lower-dimensional closed-form solution — which the paper seeks to discuss, please correct me if you read differently — is tantalizing, if only because it opens the path to different math, which can lead to optimization.