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.




Everyone knows that they have a lot of different "channels" in their head - like, what are you thinking right now? You're thinking about work, probably, because work is always on your mind. But what about the rest of your life? Did you think about how much you loved that vacation to DisneyWorld last year? Did you think about the new person you met this month at the coffee shop downtown? OmeTV  is a movement where people share personal stories and there's no effort to hide who any person is or what they've done in life. It's an open source platform for people to feel free to be themselves and explore beyond traditional society's boundaries with unlimited freedom.


page 5

page 6

page 8

page 12


Topological Approaches to Deep Learning

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

How deep learning works --The geometry of deep learning

Why and how that deep learning works well on different tasks remains a m...

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

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

A Topological Framework for Deep Learning

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

Topological Deep Learning: Classification Neural Networks

Topological deep learning is a formalism that is aimed at introducing to...

Extracting Global Dynamics of Loss Landscape in Deep Learning Models

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

Learning Connectivity of Neural Networks from a Topological Perspective

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

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.