מתי היסטוריה של רשת מגלה את עתידה ללמוד טוב יותר ממצבה הנוכחי?

תקציר מקורי באנגליתarXiv:2610.09621v1 Announce Type: new Abstract: Networks that behave alike now can still learn differently when training continues. Work on loss of plasticity and critical periods shows that the path to a state shapes what follows; it does not show whether the path carries information that a measurement of the state itself misses. We ask when the training history of a network predicts its future learning better than its current state. In a main study, small multilayer perceptrons were trained under three history regimes (42 histories), and future learning was measured at four checkpoints by a short probe: a copy of the network trained for 100 updates on a new task. Before the prediction result was read, the protocol checked the probe. It responded monotonically to a function-preserving res