量化流形：生成对抗网络学习的流形是否收敛于真实数据的流形

Mar, 2024

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

Anupam Chaudhuri, Anj Simmons, Mohamed Abdelrazek

TL;DR此论文通过实验分析了通过机器学习模型学习到的流形，比较了每个纪元学习到的流形与真实数据流形的差异，并研究了流形的内在维度和拓扑特征，以及这些度量随着模型训练的变化和趋于真实数据流形度量的趋势。

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.