Quantifying Manifolds: Do the manifolds learned by Generative Adversarial Networks converge to the real data manifold

arXiv:2403.05033v1 Announce Type: new
Abstract: 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 …

abstract adversarial arxiv converge cs.ai cs.lg data experiment gan gan model generative generative adversarial networks manifold ml models networks paper real data train type