The ability of a brain or a neural network to efficiently learn depends crucially on both the task structure and the learning rule.

Weproposetorepresent shapesasthedeformation andcombination oflearnable elementary 3D structures, which are primitives resulting from training over a collection of shapes.

Then the phenomenon has been thought as inevitable. However, the phenomenon seldom occurs in the context of recent deep learning. There is a gap between theory and reality.

In this paper we use explainability queries to formally compare the interpretability of machinelearningmodels.

A central question in computational neuroscience is how structure determines functioninneuralnetworks.