Dropout vs. batch normalization: an empirical study of their impact to deep learning

By Christian Garbin, Xingquan Zhu, Oge Marques. Multimedia tools and applications, 2020

510 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A critical review of RNN and LSTM variants in hydrological time series predictions (2024, background): “…selection of appropriate hyperparameters, such as the number of layers, the size of hidden states, learning rate, batch size, and dropout rate, can Limited by network depth and complexity [ 112 ] impact a model’s ability to capture temporal dependencies and generalize to unseen data [ 119 , 120 ].”
Machine learning techniques for analysis of hyperspectral images to determine quality of food products: A review (2021, background): “However, a study by Garbin et al. (2020) provided some suggestions in using the batch normalization and dropout strategy.”