News for hackers. Stuff that matters.

A comment on 200-Year-Old Math Opens Up AI’s Mysterious Black Box. Parent comment

Re:200-Year-Old Math Opens Up AI’s Mysterious Black Box by thearn4 on Tuesday February 28, 2023 @09:30AM (#34969663)
In my area, every controls engineer says "we can just use a PID".

99% of the time it seems they're not wrong, despite control engineering being a pretty large area of research.

[ Parent | on HN ]
Re:200-Year-Old Math Opens Up AI’s Mysterious Black Box by elevation on Tuesday February 28, 2023 @10:01AM (#34970002)
I'm nominally familiar with PID loops but am not a control engineer. What other tools would you commonly bring to bear when a PID is not applicable?
[ Parent | on HN ]
Re:200-Year-Old Math Opens Up AI’s Mysterious Black Box by sitkack on Tuesday February 28, 2023 @10:12AM (#34970153)
And a simple PID controller built with op-amps looks an awful lot like a simple neural network.

http://www.ecircuitcenter.com/Circuits/op_pid/op_pid.htm

https://www.nutsvolts.com/magazine/article/the_perceptron_ci...

[ Parent | on HN ]
Re:200-Year-Old Math Opens Up AI’s Mysterious Black Box by mordae on Tuesday February 28, 2023 @10:59AM (#34970733)
Isn't gradient descent basically PID over parameters? And tricks like momentum basically a low-pass filter integrated in the PID loop? It's quite weird how not that many concepts from analog electronics domain have gotten carried over to ML.
[ Parent | on HN ]