Neural Network Ensemble

Neural network ensembles combine predictions from multiple independently trained neural networks to improve model accuracy, robustness, and uncertainty quantification. Current research focuses on developing efficient ensemble methods, including dynamic weighting of individual network predictions and the use of diverse architectures like convolutional and recurrent networks, often within a probabilistic forecasting framework. This approach is proving valuable across diverse applications, from improving power grid stability and electricity price forecasting to enhancing the reliability of image classification and natural language processing tasks, particularly in scenarios with limited data or adversarial attacks. The resulting improved performance and uncertainty estimates are significant for both scientific understanding and real-world deployment of machine learning models.

Papers

October 6, 2024

Dynamic Post-Hoc Neural Ensemblers
Sebastian Pineda Arango, Maciej Janowski, Lennart Purucker, Arber Zela, Frank Hutter, Josif Grabocka
Ensemble Method Ensemble Diversity Ensemble Prediction Neural Network Ensemble

April 23, 2024

Probabilistic forecasting of power system imbalance using neural network-based ensembles
Jonas Van Gompel, Bert Claessens, Chris Develder
Uncertainty Estimation Probabilistic Forecast Power Flow Neural Network Ensemble

April 3, 2024

On-line conformalized neural networks ensembles for probabilistic forecasting of day-ahead electricity prices
Alessandro Brusaferri, Andrea Ballarino, Luigi Grossi, Fabrizio Laurini
Probabilistic Forecast Online Service Conformal Inference Distributional Learning Day Ahead Neural Network Ensemble

February 12, 2024

Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble
Yunzhe Xue, Usman Roshan
Adversarial Attack Black Box Cross Entropy Neural Network Ensemble

February 8, 2024

Reduced-order modeling of unsteady fluid flow using neural network ensembles
Rakesh Halder, Mohammadmehdi Ataei, Hesam Salehipour, Krzysztof Fidkowski, Kevin Maki
Long Short Term Memory Reduced Order Neural Network Ensemble Unsteady Flow

February 5, 2024

Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning
Abdelhakim Benechehab, Albert Thomas, Balázs Kégl
Offline Reinforcement Learning Model Based Reinforcement Learning Policy OpTimization Model Learning Model Based Offline Reinforcement Learning Neural Network Ensemble Model Rollouts

January 30, 2024

Detecting Racist Text in Bengali: An Ensemble Deep Learning Framework
S. S. Saruar, Nusrat, Sadia
Novel Dataset Bangla Text BERT Embeddings Neural Network Ensemble Deviant Racist Behaviour

November 23, 2023

Subnetwork Ensembles
Tim Whitaker
Deep Neural Network Generalization Performance Neural Network Ensemble Low Cost Ensemble

September 12, 2023

Epistemic Modeling Uncertainty of Rapid Neural Network Ensembles for Adaptive Learning
Atticus Beachy, Harok Bae, Jose Camberos, Ramana Grandhi
Neural Network Epistemic Uncertainty Adaptive Learning Neural Network Ensemble SNN Architecture Hypersonic Flow Aerospace Engineering

August 23, 2023

Open-set Face Recognition with Neural Ensemble, Maximal Entropy Loss and Feature Augmentation
Rafael Henrique Vareto, Manuel Günther, William Robson Schwartz
Face Recognition Open Set Feature Augmentation Facial Data Neural Network Ensemble Face Datasets Compact Neural Network Entropy Function

June 23, 2023

Minibatch training of neural network ensembles via trajectory sampling
Jamie F. Mair, Luke Causer, Juan P. Garrahan
Training Data MNIST Dataset Neural Network Ensemble Iterative Neural Network Trajectory Sampling Minibatch Stochastic

June 5, 2023

Input-gradient space particle inference for neural network ensembles
Trung Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski
Ensemble Learning Deep Ensemble Ensemble Method Neural Network Ensemble Particle Based Variational Inference Input Gradient

March 4, 2023

Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes
Thomas Philippon, Christian Gagné
Adversarial Robustness Diverse Ensemble Structured Output Robustness Evaluation Better Robustness Adaptive Attack Ensemble Diversity Neural Network Ensemble

February 20, 2023

Quantifying uncertainty for deep learning based forecasting and flow-reconstruction using neural architecture search ensembles
Romit Maulik, Romain Egele, Krishnan Raghavan, Prasanna Balaprakash
Deep Learning Uncertainty Quantification Neural Architecture Search High Uncertainty Anticipation State of the Art Forecasting Ensemble Based Neural Network Ensemble Novel Ensemble Flow Reconstruction Ensemble Uncertainty

February 1, 2023

Pathologies of Predictive Diversity in Deep Ensembles
Taiga Abe, E. Kelly Buchanan, Geoff Pleiss, John P. Cunningham
Deep Ensemble Neural Network Ensemble Pathological Feature

October 28, 2022

End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
Tamás Grósz, Mittul Singh, Sudarsana Reddy Kadiri, Hemant Kathania, Mikko Kurimo
Feature Selection Speech Processing Neural Network Ensemble Computational Paralinguistics Ensemble Feature

October 19, 2022

Adaptive Neural Network Ensemble Using Frequency Distribution
Ungki Lee, Namwoo Kang
Ensemble Method Ensemble Prediction Neural Network Ensemble

September 22, 2022

Training neural network ensembles via trajectory sampling
Jamie F. Mair, Dominic C. Rose, Juan P. Garrahan
Machine Learning Diffusion Explainer Stochastic System Neural Network Ensemble Trajectory Sampling Anomalous Trajectory

May 19, 2022

Capturing cross-session neural population variability through self-supervised identification of consistent neuron ensembles
Justin Jude, Matthew G. Perich, Lee E. Miller, Matthias H. Hennig
High Dimensional Neural Recording Neural Population Neural Network Ensemble Dead Neuron Multiple Domain

November 29, 2021

On the Effectiveness of Neural Ensembles for Image Classification with Small Datasets
Lorenzo Brigato, Luca Iocchi
Deep Neural Network Image Classification Small Datasets Shallow Network Neural Network Ensemble Neuronal Ensemble

Neural Network Ensemble

Papers

Dynamic Post-Hoc Neural Ensemblers

Probabilistic forecasting of power system imbalance using neural network-based ensembles

On-line conformalized neural networks ensembles for probabilistic forecasting of day-ahead electricity prices

Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble

Reduced-order modeling of unsteady fluid flow using neural network ensembles

Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning

Detecting Racist Text in Bengali: An Ensemble Deep Learning Framework

Subnetwork Ensembles

Epistemic Modeling Uncertainty of Rapid Neural Network Ensembles for Adaptive Learning

Open-set Face Recognition with Neural Ensemble, Maximal Entropy Loss and Feature Augmentation

Minibatch training of neural network ensembles via trajectory sampling

Input-gradient space particle inference for neural network ensembles

Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes

Quantifying uncertainty for deep learning based forecasting and flow-reconstruction using neural architecture search ensembles

Pathologies of Predictive Diversity in Deep Ensembles

End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks

Adaptive Neural Network Ensemble Using Frequency Distribution

Training neural network ensembles via trajectory sampling

Capturing cross-session neural population variability through self-supervised identification of consistent neuron ensembles

On the Effectiveness of Neural Ensembles for Image Classification with Small Datasets