undefined | Better HN

0 pointscurrymj1y ago0 comments

if you have an MNIST classifier that just takes in images, and spits out a probability of digits 1-9, that wouldn't necessarily be generative, if it is only capable of modeling P(which digit | all pixels).

But many other types of model would give you a joint distribution P(which digit, all pixels), so would be generative. Even if you only used it for classification.

https://en.wikipedia.org/wiki/Generative_model

I guess these days "generative" must mean "it is used to generate outputs that look like the training data".

But until recently, the meaning had to do with the information in the model, not how it's used.

0 comments

zozbot2341y ago

You can derive the latter information (the joint distribution), given the former and a prior over "all pixels"-like data. So, the defining feature of "generative" models is that they feature a prior over their input data?

Nimitz141y ago

Generative models model the data, whether that is p(x) or p(x,y) or (x,y,z) etc.

currymjOP1y ago

Yes, though maybe not explicitly written down.

j / k navigate · click thread line to collapse