Showing cs.NEShow all
2 papers · 1 filter
cs.NE2025
Recursive Self-Similarity in Deep Weight Spaces of Neural Architectures: A Fractal and Coarse Geometry Perspective
Ambarish Moharil, Indika Kumara, Damian Andrew Tamburri +2
This paper conceptualizes the Deep Weight Spaces (DWS) of neural architectures as hierarchical, fractal-like, coarse geometric structures observable at discrete integer scales thro…
cs.NE2024
A Scale-Invariant Diagnostic Approach Towards Understanding Dynamics of Deep Neural Networks
Ambarish Moharil, Damian Tamburri, Indika Kumara +2
This paper introduces a scale-invariant methodology employing \textit{Fractal Geometry} to analyze and explain the nonlinear dynamics of complex connectionist systems. By leveragin…