Y would be a target variable that one wants to predict, e.g. in supervised learning.
In other words, one wants to learn a model that predicts Y from X. As an intermediate step, one creates a representation T of X. T does not need to keep *all* information about X, but it needs to keep enough information to be able to extract Y from it. The remaining information about X is minimized.
Hm, I don’t understand what Y is supposed to be here.
Y would be a target variable that one wants to predict, e.g. in supervised learning.
In other words, one wants to learn a model that predicts Y from X. As an intermediate step, one creates a representation T of X. T does not need to keep *all* information about X, but it needs to keep enough information to be able to extract Y from it. The remaining information about X is minimized.
Does this clarify it?
Yes, thanks!