# Analysis of dropout learning regarded as ensemble learning

arXiv: https://arxiv.org/abs/1706.06859 · HTML: https://mlsanity.com/paper/1706.06859/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2017.

## Built on by (most cited first, 15 of 15)

- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering](https://mlsanity.com/paper/2504.09491/) (2025)
- [Ensemble-based Uncertainty Quantification: Bayesian versus Credal Inference](https://mlsanity.com/paper/2107.10384/) (2021)
- [Posterior Uncertainty Quantification in Neural Networks using Data Augmentation](https://mlsanity.com/paper/2403.12729/) (2024)
- [MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning](https://mlsanity.com/paper/2109.10552/) (2021)
- [Continual learning with the neural tangent ensemble](https://mlsanity.com/paper/2408.17394/) (2024)
- [SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting](https://mlsanity.com/paper/2602.16220/) (2026)
- [Simmering: Sufficient is better than optimal for training neural networks](https://mlsanity.com/paper/2410.19912/) (2024)
- [Exploring Dropout Discriminator for Domain Adaptation](https://mlsanity.com/paper/2107.04231/) (2021)
- [Why Neural Networks Work](https://mlsanity.com/paper/2211.14632/) (2022)
- [Classifying Tweet Sentiment Using the Hidden State and Attention Matrix of a Fine-tuned BERTweet Model](https://mlsanity.com/paper/2109.14692/) (2021)
- [Dropout Prediction Uncertainty Estimation Using Neuron Activation Strength](https://mlsanity.com/paper/2110.06435/) (2021)
- [Towards Multimodal Depth Estimation from Light Fields](https://mlsanity.com/paper/2203.16542/) (2022)
- [UCINet0: A Machine Learning based Receiver for 5G NR PUCCH Format 0](https://mlsanity.com/paper/2404.15243/) (2024)
- [Slim multi-scale convolutional autoencoder-based reduced-order models for interpretable features of a complex dynamical system](https://mlsanity.com/paper/2501.03070/) (2025)

## Abstract (arXiv)

Deep learning is the state-of-the-art in fields such as visual object recognition and speech recognition. This learning uses a large number of layers, huge number of units, and connections. Therefore, overfitting is a serious problem. To avoid this problem, dropout learning is proposed. Dropout learning neglects some inputs and hidden units in the learning process with a probability, p, and then, the neglected inputs and hidden units are combined with the learned network to express the final output. We find that the process of combining the neglected hidden units with the learned network can be regarded as ensemble learning, so we analyze dropout learning from this point of view.