[amirkdv]

That's indeed mathematically very exciting and reason enough to study IG.

But does IG allow us to reason about Neural Nets in new ways that could move the needle on open questions about information representation in ANNs or, even better, BNNs?

[antixk]

Good question. Most people are focussing on the natural gradient and making it as efficient as SGD. But some have been exploring if we can introduce inductive bias in the function space rather than the weight space, using IG. But it is still quite a new field.

[ogogmad]

BNNs?

[jmt_]

They're distinguishing between artificial neural networks(ANN) and biological neural networks(BNN)