Stephen Wolfram

FEBRUARY 14, 2023

First, there’s the matter of what architecture of neural net one should use for a particular task. One might have thought that for every particular kind of task one would need a different architecture of neural net. OK, so let’s say one’s settled on a certain neural net architecture.

Computer 145

Computer Architecture Mathematics Construction 145

Stephen Wolfram

NOVEMBER 10, 2021

But it’s a fundamental claim that we’re making—that can be thought of as a matter of natural science—that in our universe only computation can occur, not hypercomputation. And this is where our pieces of “falsifiable natural science” come in. At a purely formal level, there’s nothing wrong with hyperruliads.

Physics 121

Physics Mathematics Computer Construction 121

Stephen Wolfram

MARCH 15, 2023

Inevitably there has to be some underlying model for how to do that following—typically in practice just defined by “what a neural net with a certain architecture will do”. Processes in nature—like, for example, the weather—can be thought of as corresponding to computations. But will the result be “right”?

Computer 105

Computer Biology Mathematics Economics 105

Stephen Wolfram

FEBRUARY 2, 2023

In early 1984 I visited MIT to use the machine to try to do what amounted to natural science, systematically studying 2D cellular automata. But mostly the cellular automaton machine was used in a maddeningly “Look at this cool thing!” mode, often accompanied by rapid physical rewiring.

Physics 95

Physics Computer Mathematics Science 95