[mjburgess]

If you have explanatory models constraining the space of possible function fits, etc. etc. then I concede the point -- though, I rather regard it as my point.

The comment I replied to used "AI" in its generic sense which I take to name the theory-free frequentist stats currently in vogue. I don't regard theories as AI -- so adding physics to a NN is, in large part, computational physics. You can call it "AI", but then so-goes any use of a computer model of any kind.

[partitioned]

Well, the difference is the data-driven aspect of parts of the model. While its constrained by physics during the learning process it isn't just running a forward physics model to get the solution. The upfront computational load and extremely fast inference times through parameterization IS what makes it AI, and what makes it useful versus a normal numerical computer model.

[mjburgess]

Physics has used "empirical/phenomenological models" where curve-fitting to data has served to preclude the need for simulation, or if it's computationally intractable, etc. I'd agree that it had been underused, since I'd say such modelling is held somewhat in contempt as giving up on doing physics.

Do you have a paper that discusses any of this work in these terms? I'm presently writing a larger survey on XAI towards a theory-informed approach, and it seems these mixed models might have some novel explanatory upside/needs. At the moment i'm inclined to partition the world into theory-based and theory-free.