Thoughts on neural networks "discovering" physical concepts

[sphyrch]

(sorry i post this here now because i didn't know about this sub forum earlier)

I came across an interesting paper from which I'll quote parts of the intro:

[...] the physical theories we know may not necessarily be the simplest ones to explain the experimental data, but rather the ones that most naturally followed from a previous theory at the time. The formalism of quantum theory, for instance, is built upon classical mechanics; it has been impressively successful, but leads to conceptually challenging consequences [...]

This raises an interesting question: are the laws of quantum physics, and other physical theories more generally, the most natural ones to explain data from experiments if we assume no prior knowledge of physics? [...] we investigate whether neural networks can be used to discover physical concepts in classical and quantum mechanics from experimental data, without imposing prior assumptions and restrictions on the space of possible concepts.

and the conclusion:

[...] we have shown that neural networks can be used to recover physical variables from experimental data. To do so, we have introduced a new network structure, SciNet, and employed techniques from unsupervised representation learning to encourage the network to and a minimal uncorrelated representation of experimental data. [...] Furthermore, the analogy between the process of reasoning of a physicist and representation learning provides insight about ways to formalize physical reasoning without adding prior knowledge about the system.

obviously the authors are more competent in Physics than I am - so are most PF member. what are your opinions on this? can the work of these authors "discover" physical laws in any way or is the paper title misleading?

would stuff like special relativity or quantum mechanics be discovered purely from experimental data without using prior knowledge? even if physical laws were encoded by these networks as "black box" models, would they be a good replacement of closed-form expressions or differential equation solutions?

 

[Andrew Mason]

I am not sure what the authors are seeking to achieve. It seems to me that some very good neural networks were actively engaged in developing quantum theory.

Experience shows that human neural networks are good at creating mathematical models of the physical world. It will likely be even better with the assistance of fast computational machines that can process large volumes of data and find patterns and relationships. Molecular biology rather than physics might be a better area to focus on

AM