ארבע דרכים לגידול מסווג ולמה אחת מהן לא יכולה ללמוד

תקציר מקורי באנגליתarXiv:2610.00180v1 Announce Type: new Abstract: Constructive classifiers add structure while they train: a level to a tree, a unit to a hidden layer, a split at a leaf. This paper asks what each of four such growth decisions actually buys, measured under one fixed protocol in tree-structured and constructive models, and gives an exact diagnosis and a fix for the one that buys nothing. The diagnosis concerns the most natural way to deepen a soft decision tree: turn every leaf into a gate whose two children inherit the parent's class distribution, so that the function is unchanged. I prove that this leaves the gradient of every new gate identically zero and, with the gate at 1/2, gives the two children identical gradients, so the added level can never learn. Unlike the symmetry that Net2Net