In this paper, we explore a space-time geometric view of signal representation in machine learning models. The question we are interested in is if we can identify what is causing signal representation errors – training data inadequacies, model insufficiencies, or both. Loosely expressed, this problem is stylistically similar to blind deconvolution problems. However, studies of space-time geometries might be able to partially solve this problem by considering the curvature produced by mass in (Anti-)de Sitter space. We study the effectiveness of our approach on the MNIST dataset.
Suhas Sreehari, Pradeep Ramuhalli, Frank Liu, "Differential Geometric View of Information Flow in Neural Nets" in Electronic Imaging, 2025, pp 141-1 - 141-10, https://doi.org/10.2352/EI.2025.37.14.COIMG-141