Do deep nets really need weight decay and dropout?

20 February 2018

Alex Hernández-García

Papers citing "Do deep nets really need weight decay and dropout?"

4 / 4 papers shown

Title
A Data-Augmentation Is Worth A Thousand Samples: Exact Quantification From Analytical Augmented Sample Moments Randall Balestriero Ishan Misra Yann LeCun 35 20 0 16 Feb 2022
Further advantages of data augmentation on convolutional neural networks Alex Hernández-García Peter König 8 107 0 26 Jun 2019
Data augmentation instead of explicit regularization Alex Hernández-García Peter König 30 141 0 11 Jun 2018
A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay L. Smith 208 1,020 0 26 Mar 2018