Deep Learning Over-Parameterization: the Shallow Fallacy

Pierre Baldi. Deep Learning Over-Parameterization: the Shallow Fallacy. In Tetiana Lutchyn, Adín Ramírez Rivera, Benjamin Ricaud, editors, Northern Lights Deep Learning Conference, NLDL 2024, 9-11 January 2024, UiT The Arctic University, Tromsø, Norway. Volume 233 of Proceedings of Machine Learning Research, pages 7-12, PMLR, 2024. [doi]

Abstract

Abstract is missing.