Ensembling neural networks: Many could be better than all

2002/05/01 by Zhi-Hua Zhou, Zhi‐Hua Zhou, Jianxin Wu +1 · 60 citations
Computer Science · #Neural Networks and Applications #Face and Expression Recognition #Machine Learning and Data Classification

paper · doi:10.1016/s0004-3702(02)00190-x

Cited by

• Learning similarity with cosine similarity ensemble
• Neural network ensemble-based sensitivity analysis in structural engineering: Comparison of selected methods and the influence of statistical correlation
• Isolating Compiler Faults via Multiple Pairs of Adversarial Compilation Configurations
• Neural network approach to classifying alarming student responses to online assessment
• Selective Ensembles for Consistent Predictions
• Ensemble Performance Through the Lens of Linear Independence of Classifier Votes in Data Streams
• Eliminating Multicollinearity Issues in Neural Network Ensembles: Incremental, Negatively Correlated, Optimal Convex Blending
• Exploring the Utilities of the Rationales from Large Language Models to Enhance Automated Essay Scoring
• Improved genomic prediction performance with ensembles of diverse models
• Neural Ensemble Search for Uncertainty Estimation and Dataset Shift
• DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation
• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
• Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
• Soft Gradient Boosting Machine
• ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification
• Activation Ensembles for Deep Neural Networks
• Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs
• A novel ensemble model for multi-temporal forest vegetation classification: integrating spectral-temporal features and topographic constraints
• Graphical Representation for Heterogeneous Face Recognition
• Deep Learning for Medical Image Segmentation
• Ensemble Pruning via Margin Maximization
• Diversity inducing Information Bottleneck in Model Ensembles
• Sympathy for the Details: Dense Trajectories and Hybrid Classification\n Architectures for Action Recognition
• Neural network ensembles: Evaluation of aggregation algorithms
• Minimally Supervised Feature Selection for Classification (Master's Thesis, University Politehnica of Bucharest)
• IEA: Inner Ensemble Average within a convolutional neural network
• Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs
• Generating Efficient DNN-Ensembles with Evolutionary Computation
• PSEO: Optimizing Post-hoc Stacking Ensemble Through Hyperparameter Tuning
• A K-means-based Multi-subpopulation Particle Swarm Optimization for\n Neural Network Ensemble
• Systematic Ensemble Learning for Regression
• Theoretical Investigation of Composite Neural Network
• Pruning variable selection ensembles
• Principal Model Analysis Based on Partial Least Squares
• Personalized Classifier Ensemble Pruning Framework for Mobile Crowdsourcing
• Infection status outcome, machine learning method and virus type interact to affect the optimised prediction of hepatitis virus immunoassay results from routine pathology laboratory assays in unbalanced data. [europepmc]
• Big data integration shows Australian bush-fire frequency is increasing significantly. [europepmc]
• High-dimensional omics data analysis using a variable screening protocol with prior knowledge integration (SKI). [europepmc]
• A Selective Ensemble Classification Method Combining Mammography Images with Ultrasound Images for Breast Cancer Diagnosis. [europepmc]
• HRV-derived data similarity and distribution index based on ensemble neural network for measuring depth of anaesthesia. [europepmc]
• Biomedical Text Categorization Based on Ensemble Pruning and Optimized Topic Modelling. [europepmc]
• A generalised framework for detailed classification of swimming paths inside the Morris Water Maze. [europepmc]
• Machine Learning Methods Applied to Predict Ventilator-Associated Pneumonia with Pseudomonas aeruginosa Infection via Sensor Array of Electronic Nose in Intensive Care Unit. [europepmc]
• Margin-Based Pareto Ensemble Pruning: An Ensemble Pruning Algorithm That Learns to Search Optimized Ensembles. [europepmc]
• Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity Recognition. [europepmc]
• Deeper Profiles and Cascaded Recurrent and Convolutional Neural Networks for state-of-the-art Protein Secondary Structure Prediction. [europepmc]
• Non-invasive platform to estimate fasting blood glucose levels from salivary electrochemical parameters. [europepmc]
• A Novel Framework with High Diagnostic Sensitivity for Lung Cancer Detection by Electronic Nose. [europepmc]
• Robust Soft Sensor with Deep Kernel Learning for Quality Prediction in Rubber Mixing Processes. [europepmc]
• Genetic Deep Convolutional Autoencoder Applied for Generative Continuous Arterial Blood Pressure via Photoplethysmography. [europepmc]
• Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography. [europepmc]
• The whole is greater than its parts: ensembling improves protein contact prediction. [europepmc]
• Permutation-based identification of important biomarkers for complex diseases via machine learning models. [europepmc]
• Employing Multimodal Machine Learning for Stress Detection. [europepmc]
• Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020. [europepmc]
• Machine Learning Approach for Application-Tailored Nanolubricants' Design. [europepmc]
• Prediction of ground vibration due to mine blasting in a surface lead-zinc mine using machine learning ensemble techniques. [europepmc]
• Modeling interfacial tension of surfactant-hydrocarbon systems using robust tree-based machine learning algorithms. [europepmc]
• Distinctive properties of biological neural networks and recent advances in bottom-up approaches toward a better biologically plausible neural network. [europepmc]
• Improved genomic prediction performance with ensembles of diverse models. [europepmc]