I got fooled by AI-for-science hype–here's what it taught me

Re:I got fooled by AI-for-science hype–here's what it taught me by constantcrying on Tuesday May 20, 2025 @04:06AM (#44039016)

This does not apply to PINNs though. They were used and investigated by people deeply knowledgeable about numerics and neural networks, they just totally failed to live up to expectation.

[ Parent | on HN ]

Re:I got fooled by AI-for-science hype–here's what it taught me by tonii141 on Tuesday May 20, 2025 @04:14AM (#44039066)

"they just totally failed to live up to expectation"

Because the expectation was too high. If you are aiming for precision, neural networks might not be the best solution for you. That is why generative AI works so well, it doesn’t need to be extremely precise. On the other hand you don't see people use neural networks in system control for cricital processes.

[ Parent | on HN ]

Re:I got fooled by AI-for-science hype–here's what it taught me by sgt101 on Tuesday May 20, 2025 @07:04AM (#44040115)

Apart from self driving and autonomous flying...

[ Parent | on HN ]

Re:I got fooled by AI-for-science hype–here's what it taught me by tonii141 on Tuesday May 20, 2025 @07:18AM (#44040217)

AI is used in scene understanding for those applications, but there is no neural network that is steering the wheel.

[ Parent | on HN ]