Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
Abstract
We introduce a simple and effective method for regularizing large convolutional neural networks. We replace the conventional deterministic pooling operations with a stochastic procedure, randomly picking the activation within each pooling region according to a multinomial distribution, given by the activities within the pooling region. The approach is hyper-parameter free and can be combined with other regularization approaches, such as dropout and data augmentation. We achieve state-of-the-art performance on four image datasets, relative to other approaches that do not utilize data augmentation.
Cite
Text
Zeiler and Fergus. "Stochastic Pooling for Regularization of Deep Convolutional Neural Networks." International Conference on Learning Representations, 2013.Markdown
[Zeiler and Fergus. "Stochastic Pooling for Regularization of Deep Convolutional Neural Networks." International Conference on Learning Representations, 2013.](https://mlanthology.org/iclr/2013/zeiler2013iclr-stochastic/)BibTeX
@inproceedings{zeiler2013iclr-stochastic,
title = {{Stochastic Pooling for Regularization of Deep Convolutional Neural Networks}},
author = {Zeiler, Matthew D. and Fergus, Rob},
booktitle = {International Conference on Learning Representations},
year = {2013},
url = {https://mlanthology.org/iclr/2013/zeiler2013iclr-stochastic/}
}