Computer scientists prove why bigger neural networks do better

Re:Computer scientists prove why bigger neural networks do b... by acchow on Thursday February 10, 2022 @02:38PM (#30291364)

Doesn't this demonstrate the opposite of what you were claiming?

[ Parent | on HN ]

Re:Computer scientists prove why bigger neural networks do b... by lacksconfidence on Thursday February 10, 2022 @02:48PM (#30291486)

I feel like the quotes agree with parent:

> “If something happens very slowly over quite some time, maybe over decades, the different parts of the brain take up functions that would normally be done by the part that is pushed to the side,” adds Muenke, who was not involved in the case.

[ Parent | on HN ]

Re:Computer scientists prove why bigger neural networks do b... by Ajedi32 on Thursday February 10, 2022 @02:50PM (#30291509)

Did you see the scans? The dude's head is practically empty (brain 55-75% smaller than normal) and nobody even noticed until he was 44 years old and got an MRI.

[ Parent | on HN ]

Re:Computer scientists prove why bigger neural networks do b... by divbzero on Thursday February 10, 2022 @02:52PM (#30291533)

I think it’s that a priori you would expect a hollow brain to have a far more drastic effect and not allow for a mostly normal adult life.

[ Parent | on HN ]

Re:Computer scientists prove why bigger neural networks do b... by pishpash on Thursday February 10, 2022 @03:06PM (#30291709)

Why would you expect that, when a tiny insect can do pretty intelligent things? What "unexpected" things humans can do are probably all in the >75 IQ range.

[ Parent | on HN ]