Ensemble deep learning: A review

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.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Temporal Ensembling for Semi-Supervised Learning
• The Loss Surfaces of Multilayer Networks
• Random vector functional link network: recent developments, applications, and future directions
• AdaNet: Adaptive Structural Learning of Artificial Neural Networks
• Incremental Boosting Convolutional Neural Network for Facial Action Unit Recognition
• Multi-label ensemble based on variable pairwise constraint projection
• Sparse Deep Stacking Network for Image Classification
• Unsupervised Feature Learning with K-means and An Ensemble of Deep Convolutional Neural Networks for Medical Image Classification
• Generalized Negative Correlation Learning for Deep Ensembling

Cited by in corpus (60)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Comprehensive Review On Twin Support Vector Machines
• Random vector functional link network: recent developments, applications, and future directions
• Deep Learning for Brain Age Estimation: A Systematic Review
• A generative artificial intelligence framework based on a molecular diffusion model for the design of metal-organic frameworks for carbon capture
• SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification
• Uncertainty Quantification in Multivariable Regression for Material Property Prediction with Bayesian Neural Networks
• Benchmarking highly entangled states on a 60-atom analog quantum simulator
• Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model
• Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge
• Seamless lightning nowcasting with recurrent-convolutional deep learning
• Optimized ensemble deep learning framework for scalable forecasting of dynamics containing extreme events
• Efficient Adaptive Ensembling for Image Classification
• Evaluation of Thermal Imaging on Embedded GPU Platforms for Application in Vehicular Assistance Systems
• Adaptive Modeling of Satellite-Derived Nighttime Lights Time-Series for Tracking Urban Change Processes Using Machine Learning
• Graph Neural Networks for Surfactant Multi-Property Prediction
• DNNShifter: An Efficient DNN Pruning System for Edge Computing
• The VoxCeleb Speaker Recognition Challenge: A Retrospective
• Evaluating Generic Auto-ML Tools for Computational Pathology
• Deep Learning to Estimate Permeability using Geophysical Data
• Filter Drug-induced Liver Injury Literature with Natural Language Processing and Ensemble Learning
• Predicting the Temperature Dependence of Surfactant CMCs Using Graph Neural Networks
• Streamlined Lensed Quasar Identification in Multiband Images via Ensemble Networks
• An Ensemble Machine Learning Approach for Tropical Cyclone Detection Using ERA5 Reanalysis Data
• Applications of Spiking Neural Networks in Visual Place Recognition
• Decoding Cognitive Health Using Machine Learning: A Comprehensive Evaluation for Diagnosis of Significant Memory Concern
• MANSY: Generalizing Neural Adaptive Immersive Video Streaming With Ensemble and Representation Learning
• STAP: Sequencing Task-Agnostic Policies
• DIGS: Deep Inference of Galaxy Spectra with Neural Posterior Estimation
• Attention-based Multi-fidelity Machine Learning Model for Computational Fractional Flow Reserve Assessment
• Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inference
• Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions
• Deep Evidential Learning for Radiotherapy Dose Prediction
• Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation
• E Pluribus Unum Interpretable Convolutional Neural Networks
• Learning Feynman integrals from differential equations with neural networks
• Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks
• Robust and Explainable Framework to Address Data Scarcity in Diagnostic Imaging
• Exploring CNN-based models for image's aesthetic score prediction with using ensemble
• Deep Neural Networks for Automatic Speaker Recognition Do Not Learn Supra-Segmental Temporal Features
• Calibrated Bagging Deep Learning for Image Semantic Segmentation: A Case Study on COVID-19 Chest X-ray Image
• Testing Outlier Detection Algorithms for Identifying Early-Stage Solute Clusters in Atom Probe Tomography
• Measuring the Substructure Mass Power Spectrum of 23 SLACS Strong Galaxy-Galaxy Lenses with Convolutional Neural Networks
• Testing Human-Hand Segmentation on In-Distribution and Out-of-Distribution Data in Human-Robot Interactions Using a Deep Ensemble Model
• Machine Learning for maximizing the memristivity of single and coupled quantum memristors
• Uncertainty estimation for time series classification: Exploring predictive uncertainty in transformer-based models for variable stars
• A machine-generated catalogue of Charon's craters and implications for the Kuiper belt
• An Expert Ensemble for Detecting Anomalous Scenes, Interactions, and Behaviors in Autonomous Driving
• "Where Can I Park?" Understanding Human Perspectives and Scalably Detecting Disability Parking from Aerial Imagery
• HealthProcessAI: A Technical Framework and Proof-of-Concept for LLM-Enhanced Healthcare Process Mining
• Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions
• Uncertainties of Satellite-based Essential Climate Variables from Deep Learning
• Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting
• Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification
• Autoencoder-based analytic continuation method for strongly correlated quantum systems
• A gradient boosting and broadband approach to finding Lyman-α emitting galaxies beyond narrowband surveys
• Multivariate unbounded quantum regression via log-ratio probabilities mitigating barren plateaus
• fMBN-E: Efficient Unsupervised Network Structure Ensemble and Selection for Clustering
• RocketStack: Level-aware Deep Recursive Ensemble Learning Architecture
• Predicting High-Flow Nasal Cannula Failure in an ICU Using a Recurrent Neural Network with Transfer Learning and Input Data Perseveration: A Retrospective Analysis