Training Deep Visual Networks Beyond Loss and Accuracy Through a Dynamical Systems Approach

arXiv:2604.09716v1 Announce Type: cross Abstract: Deep visual recognition models are usually trained and evaluated using metrics such as loss and accuracy. While these measures show whether a model is improving, they reveal very little about how its internal representations change during training. This paper introduces a complementary way to study that process by examining training through the lens of dynamical systems. Drawing on ideas from signal analysis originally used to study biological ne