Ensemble deep learning: A review

TL;DR

This paper reviews the current state of deep ensemble learning, categorizing various models and discussing their applications and future research directions in improving generalization performance.

Contribution

It provides an extensive summary and categorization of deep ensemble models, highlighting their advantages and applications across different domains.

Findings

Deep ensemble models improve generalization performance.

Various ensemble strategies like bagging, boosting, stacking are analyzed.

Applications span multiple domains with potential future research directions.

Abstract

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.