My understanding is that floating-point granularity is enough of a real problem that it does sometimes matter in realistic ML settings, which suggests that it’s probably a reasonable level of abstraction on which to analyze neural networks (whereas any additional insights from an electromagnetism-based analysis probably never matter, suggesting that’s not a reasonable/useful level of abstraction).
My understanding is that floating-point granularity is enough of a real problem that it does sometimes matter in realistic ML settings, which suggests that it’s probably a reasonable level of abstraction on which to analyze neural networks (whereas any additional insights from an electromagnetism-based analysis probably never matter, suggesting that’s not a reasonable/useful level of abstraction).