Back to articles
Proceedings Paper
Volume: 37 | Article ID: COIMG-141
Image
Differential Geometric View of Information Flow in Neural Nets
  DOI :  10.2352/EI.2025.37.14.COIMG-141  Published OnlineFebruary 2025
Abstract
Abstract

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.

Subject Areas :
Views 2
Downloads 0
 articleview.views 2
 articleview.downloads 0
  Cite this article 

Suhas Sreehari, Pradeep Ramuhalli, Frank Liu, "Differential Geometric View of Information Flow in Neural Netsin Electronic Imaging,  2025,  pp 141-1 - 141-10,  https://doi.org/10.2352/EI.2025.37.14.COIMG-141

 Copy citation
  Copyright statement 
Copyright © 2025, Society for Imaging Science and Technology
ei
Electronic Imaging
2470-1173
2470-1173
Society for Imaging Science and Technology
IS&T 7003 Kilworth Lane, Springfield, VA 22151 USA