[olliej]

So my interpretation of the neural hash approach is largely that it is essentially trading a much larger number of very small “neurons” vs a smaller number of floats. Given that I’d be curious about what the total size difference is.

I could see the hash approach at a functional level resulting in different features essentially getting a different number of bit directly, which be approximately equivalent to having a NN with variable precision floats, all in a very hand wavy way.

Eg we could say a NN/NH needs N bits of information to work accurately, in which case you’re trading the format and operations on those Nbits

[2overwhelm]

Sry, non native english speaker here... yes, you're right, but wasn't the topic about progress in building selfhealing-systems by programming in 'blocks', setting routines searching for (that i want to call an vector in terms of a setted goal) problems, and be able to slove the problems ? Or what had we learned by all the 'having crypto' when not programming in 'blocks' -so hashes seem the smallest part of how to begin, not ? puh Hope that it wasn't too non-understandable, regards