Topological Data Analysis of Neural Network Layer Representations

2022/07/01 by Archie Shahidullah, Shahidullah, Archie
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topological and Geometric Data Analysis

paper · pdf · doi:10.48550/arxiv.2208.06438

openalex publication_date 2022/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper is a cursory study on how topological features are preserved within the internal representations of neural network layers. Using techniques from topological data analysis, namely persistent homology, the topological features of a simple feedforward neural network's layer representations of a modified torus with a Klein bottle-like twist were computed. The network appeared to approximate homeomorphisms in early layers, before significantly changing the topology of the data in deeper layers. The resulting noise hampered the ability of persistent homology to compute these features, however similar topological features seemed to persist longer in a network with a bijective activation function.

Related

• Can neural networks learn persistent homology features?
• Topological Data Analysis for Neural Network Analysis: A Comprehensive Survey
• Topological Measurement of Deep Neural Networks Using Persistent Homology
• Deep neural networks architectures from the perspective of manifold learning
• Topology of deep neural networks