Partial differential equation

The goal being that maybe that can then be tied to this simple model that predicts on a whole body level what's happening, but also looking at what happens in the brain at a cellular level.

Adrienne, you might have to explain to the audience what a PDE is, a spatial model is.

Sorry about that.

No, no, that's a very good

So in a, in a napkin, literally in a napkin, he wrote the partial differential equations of the boost converter, power converter, and he solved it in, uh, five minutes.

And I said, "Really? [chuckles] Can you do that?" And then he said, "You know, there's something called Maple, and you just type in, uh, PDE solve, and it will solve it." And I, I didn't, I didn't know it, and I was so happy.

[chuckles]

And then I said, "Okay, let me..." I went back, and I, I worked the other converters, and I worked the motor, and we could solve the PDE.

[chuckles]

And I was very happy.

Yeah.

So, you know, like physics-informed neural nets are about like saying that, you know, I write down like a PDE, uh, partial differential equations, and hopefully the optimization succeeds, and I get the answer, right? And of course, if like optimization was not at all an issue, this would be universal.

You solve everything, you know, we're all happy, but that's not the case.

And so optimization ends up being usually very difficult, especially for problems that are time-dependent, meaning it's not just stationary, you also have time, and the time component in many cases could be turbulent, like in the case of fluid dynamics.

... he's, kid's good.

The one who I'm really, who needs improvement is PDE.

He [laughs] needs-

Yeah

... to start winning his matches.

He needs to just start to do something, 'cause he's been losing matches, except for that tag team match that he had that he, last week, when he won that.

So that's the only thing I would say about PDE.

Yeah, what a better way for him to, uh, Rich Swann to teach him, too, so.