Saved in:
Bibliographic Details
Main Authors: Chaudhuri, Anupam, Simmons, Anj, Abdelrazek, Mohamed
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.05033
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929268591689728
author Chaudhuri, Anupam
Simmons, Anj
Abdelrazek, Mohamed
author_facet Chaudhuri, Anupam
Simmons, Anj
Abdelrazek, Mohamed
contents This paper presents our experiments to quantify the manifolds learned by ML models (in our experiment, we use a GAN model) as they train. We compare the manifolds learned at each epoch to the real manifolds representing the real data. To quantify a manifold, we study the intrinsic dimensions and topological features of the manifold learned by the ML model, how these metrics change as we continue to train the model, and whether these metrics convergence over the course of training to the metrics of the real data manifold.
format Preprint
id arxiv_https___arxiv_org_abs_2403_05033
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantifying Manifolds: Do the manifolds learned by Generative Adversarial Networks converge to the real data manifold
Chaudhuri, Anupam
Simmons, Anj
Abdelrazek, Mohamed
Machine Learning
Artificial Intelligence
This paper presents our experiments to quantify the manifolds learned by ML models (in our experiment, we use a GAN model) as they train. We compare the manifolds learned at each epoch to the real manifolds representing the real data. To quantify a manifold, we study the intrinsic dimensions and topological features of the manifold learned by the ML model, how these metrics change as we continue to train the model, and whether these metrics convergence over the course of training to the metrics of the real data manifold.
title Quantifying Manifolds: Do the manifolds learned by Generative Adversarial Networks converge to the real data manifold
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2403.05033