Proposition 1.Let 2 (0,min(120, 1n)). Proposition 3.Let 2 (0,min(140, 1n)).

We adopt the natural assumption that the empirical NTK develops a block structure aligned with the class labels, i.e., samples within the same class have stronger

To improve the learnability of deep learning models, various techniques have been proposed.

In this paper we study the effect that this mechanism has on the function implemented bythetrainedmodel.