DeepAI AI Chat
Log In Sign Up

Topology and geometry of data manifold in deep learning

by   German Magai, et al.

Despite significant advances in the field of deep learning in applications to various fields, explaining the inner processes of deep learning models remains an important and open question. The purpose of this article is to describe and substantiate the geometric and topological view of the learning process of neural networks. Our attention is focused on the internal representation of neural networks and on the dynamics of changes in the topology and geometry of the data manifold on different layers. We also propose a method for assessing the generalizing ability of neural networks based on topological descriptors. In this paper, we use the concepts of topological data analysis and intrinsic dimension, and we present a wide range of experiments on different datasets and different configurations of convolutional neural network architectures. In addition, we consider the issue of the geometry of adversarial attacks in the classification task and spoofing attacks on face recognition systems. Our work is a contribution to the development of an important area of explainable and interpretable AI through the example of computer vision.


page 5

page 6

page 8

page 12


Deep neural networks architectures from the perspective of manifold learning

Despite significant advances in the field of deep learning in ap-plicati...

Topological Approaches to Deep Learning

We perform topological data analysis on the internal states of convoluti...

A Study on Topological Descriptors for the Analysis of 3D Surface Texture

Methods from computational topology are becoming more and more popular i...

Metric Space Magnitude and Generalisation in Neural Networks

Deep learning models have seen significant successes in numerous applica...

A Topological Framework for Deep Learning

We utilize classical facts from topology to show that the classification...

Learning Connectivity of Neural Networks from a Topological Perspective

Seeking effective neural networks is a critical and practical field in d...

Extracting Global Dynamics of Loss Landscape in Deep Learning Models

Deep learning models evolve through training to learn the manifold in wh...