This paper provides a comprehensive review of deep ensemble learning models, which combine the advantages of deep learning and ensemble learning to enhance generalization performance. The authors categorize ensemble models into bagging, boosting, stacking, negative correlation-based deep ensembles, explicit/implicit ensembles, homogeneous/heterogeneous ensembles, and decision fusion strategies. They discuss the theoretical foundations, such as bias-variance decomposition, statistical, computational, and representational aspects, and the importance of diversity among base classifiers. The paper also explores various ensemble strategies, including bagging, boosting, and stacking, and their applications in different domains. Additionally, it covers negative correlation learning, explicit/implicit ensembles, homogeneous and heterogeneous ensembles, and decision fusion techniques. The authors conclude by discussing potential future research directions in deep ensemble learning.This paper provides a comprehensive review of deep ensemble learning models, which combine the advantages of deep learning and ensemble learning to enhance generalization performance. The authors categorize ensemble models into bagging, boosting, stacking, negative correlation-based deep ensembles, explicit/implicit ensembles, homogeneous/heterogeneous ensembles, and decision fusion strategies. They discuss the theoretical foundations, such as bias-variance decomposition, statistical, computational, and representational aspects, and the importance of diversity among base classifiers. The paper also explores various ensemble strategies, including bagging, boosting, and stacking, and their applications in different domains. Additionally, it covers negative correlation learning, explicit/implicit ensembles, homogeneous and heterogeneous ensembles, and decision fusion techniques. The authors conclude by discussing potential future research directions in deep ensemble learning.