Ambarish Moharil

Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic Explainability

This paper investigates how multilayer perceptrons (MLPs) can be represented in non-Euclidean spaces, with emphasis on the Poincaré model of hyperbolic geometry. We aim to capture the geometric evolution of their weighted topology and self-organization over time. Instead of restricting analysis to s…