no code implementations • 7 Dec 2020 • Anita de Mello Koch, Ellen de Mello Koch, Robert de Mello Koch
Promising resolutions of the generalization puzzle observe that the actual number of parameters in a deep network is much smaller than naive estimates suggest.
1 code implementation • 12 Jun 2019 • Ellen de Mello Koch, Robert de Mello Koch, Ling Cheng
Although we are motivated by the connection between deep learning and RG flow, in this study we focus mainly on comparing a single layer of a deep network to a single step in the RG flow.