IntrinsicDimension,PersistentHomologyand GeneralizationinNeuralNetworks

In recent years, deep neural networks (DNNs) have become the de facto machine learning tool and have revolutionized a variety of fields such as natural language processing [DCLT18], image perception [KSH12,RBH+21],geometry processing [QSMG17,ZBL+20]and3Dvision[DBI18, GLW+21]. Despite their widespread use, little is known about their theoretical properties.