Trying to summarize this for my understanding benefit:
So the “trick” is that, instead of precisely tracking error, we just track the distribution using the Quantiliser section? (And the broader insight being that, instead of backpropping a function, we’re measuring a distribution?)
I am going to answer this comment because it is the first to address the analysis section. Thank you.
I close the paragraph saying that there is no functions anywhere and it will aggrieve some. The shift I am trying to suggest is for those who want to analyse the system using mathematics, and could be dismayed by the absence of functions to work with.
Distributions can be a place to start. The quantilisers are a place to restart mathematical analysis. I gave some links to an existing field of mathematical research that is working along those lines.
Check this out: they are looking for a multi-dimensional extension to the concept. Here it is, I suggest.
Trying to summarize this for my understanding benefit: So the “trick” is that, instead of precisely tracking error, we just track the distribution using the Quantiliser section? (And the broader insight being that, instead of backpropping a function, we’re measuring a distribution?)
I am going to answer this comment because it is the first to address the analysis section. Thank you.
I close the paragraph saying that there is no functions anywhere and it will aggrieve some. The shift I am trying to suggest is for those who want to analyse the system using mathematics, and could be dismayed by the absence of functions to work with.
Distributions can be a place to start. The quantilisers are a place to restart mathematical analysis. I gave some links to an existing field of mathematical research that is working along those lines.
Check this out: they are looking for a multi-dimensional extension to the concept. Here it is, I suggest.
Thank you!