# MaxDropout: Deep Neural Network Regularization Based on Maximum Output Values

arXiv: https://arxiv.org/abs/2007.13723 · HTML: https://mlsanity.com/paper/2007.13723/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks](https://mlsanity.com/paper/2201.03299/) (2022)
- [Advancing Spiking Neural Networks towards Multiscale Spatiotemporal Interaction Learning](https://mlsanity.com/paper/2405.13672/) (2024)
- [The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach](https://mlsanity.com/paper/2409.17370/) (2024)
- [LayerCollapse: Adaptive compression of neural networks](https://mlsanity.com/paper/2311.17943/) (2023)
- [MaxDropoutV2: An Improved Method to Drop out Neurons in Convolutional Neural Networks](https://mlsanity.com/paper/2203.02740/) (2022)

## Abstract (arXiv)

Different techniques have emerged in the deep learning scenario, such as Convolutional Neural Networks, Deep Belief Networks, and Long Short-Term Memory Networks, to cite a few. In lockstep, regularization methods, which aim to prevent overfitting by penalizing the weight connections, or turning off some units, have been widely studied either. In this paper, we present a novel approach called MaxDropout, a regularizer for deep neural network models that works in a supervised fashion by removing (shutting off) the prominent neurons (i.e., most active) in each hidden layer. The model forces fewer activated units to learn more representative information, thus providing sparsity. Regarding the experiments, we show that it is possible to improve existing neural networks and provide better results in neural networks when Dropout is replaced by MaxDropout. The proposed method was evaluated in image classification, achieving comparable results to existing regularizers, such as Cutout and RandomErasing, also improving the accuracy of neural networks that uses Dropout by replacing the existing layer by MaxDropout.