The problem is that neural networks aren’t like programs. The point is that both are correct, but we’d really prefer the first explanation, since it gives insight into what the program is doing. Then you give the computer to a superhuman physicist who studies all of the components including the state of the transistors and internal components and concludes that the wheel will spin for 9 years before the screen gives out. You give it to a computer scientist who says that the program is in an infinite loop, and the wheel will never stop spinning. Suppose you have the spinning color wheel on your MacBook.
What kind of explanation would you like to be able to get? It reminds me of something the physicist Tim Maudlin described on a recent podcast (I will give a poor summary): I guess this raises the question of levels of explanation.
0 kommentar(er)
