Ensemble deep learning: A review

By M. A. Ganaie, Minghui Hu, Mohammad Tanveer, Ponnuthurai Nagaratnam Suganthan. Engineering applications of artificial intelligence, 2021

2,013 citations recorded by the source corpus.

Ensemble learning combines several individual models to obtain better generalization performance. Currently, deep learning architectures are showing better performance compared to the shallow or traditional models. Deep ensemble learning models combine the advantages of both the deep learning models as well as the ensemble learning such that the final model has better generalization performance. This paper reviews the state-of-art deep ensemble models and hence serves as an extensive summary for the researchers. The ensemble models are broadly categorised into bagging, boosting, stacking, negative correlation based deep ensemble models, explicit/implicit ensembles, homogeneous/heterogeneous ensemble, decision fusion strategies based deep ensemble models. Applications of deep ensemble models in different domains are also briefly discussed. Finally, we conclude this paper with some potential future research directions.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/8b47a2d47e4122d56e213909591418bbb6894cf2

How researchers see this paper

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

In Artificial Intelligence

1. Florian Hartig
2. Rohitash Chandra
3. Maximilian Pichler
4. Azal Ahmad Khan
5. Omkar Chaudhari

Citations in the corpus

• Machine learning and deep learning—A review for ecologists (2022, background): “…the complexity of an ensemble model is typically related to the average complexity of its ensemble members and the differences between them, which in turn affect error and variance of the ensemble estimator (Bernardo & Smith, 2009 ; Dietterich, 2000 ; Dormann et al., 2018; Ganaie et al., 2021 ).”
• A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, methodology): “We can investigate the combination of conventional machine learning models and develop deep ensemble models [316] utilising ensemble techniques such as voting and stacking.”