Deep Ensembles
PulseAugur coverage of Deep Ensembles — every cluster mentioning Deep Ensembles across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
New research explores uncertainty quantification in deep learning for diverse applications
Three new research papers explore advanced techniques for uncertainty quantification in deep learning models. The first paper introduces intuitionistic fuzzy deep randomized neural networks (IF-dRVFL and IF-edRVFL) to i…
-
New survey details uncertainty quantification for trustworthy deep learning
A new survey paper published on arXiv details methods for uncertainty quantification in deep learning, focusing on techniques relevant for trustworthy AI in safety-critical applications. The paper categorizes approaches…
-
New method enhances neural ensemble search with surrogate models · 2 sources tracked
Researchers have developed a new method for Neural Ensemble Search (NES) that addresses the computational challenges of optimizing both individual model architectures and their ensemble composition. The approach utilize…
-
AI model forecasts sweet pepper yields using multimodal data
Researchers have developed a new multimodal deep learning framework to forecast the number of harvest-ready sweet peppers at an individual plant level. This system combines visual data processed by the DinoV3 encoder wi…
-
AI model forecasts sweet pepper yield using multimodal data
Researchers have developed a new multimodal deep learning framework to forecast the yield of sweet peppers. This framework combines visual data, processed by the DINOv3 encoder, with numerical fruit counts. Utilizing a …
-
AI crash simulation uncertainty methods compared in new research paper
A new research paper compares two uncertainty quantification methods, Monte Carlo Dropout and Deep Ensembles, for AI-driven crash simulation surrogates. The study, utilizing NVIDIA PhysicsNeMo and an open-source bumper …
-
New method disentangles model and human uncertainty in facial age estimation
Researchers have developed a method to distinguish between model uncertainty and human data uncertainty in facial age estimation tasks. By training Bayesian Neural Networks on the APPA-REAL dataset with varying data siz…
-
AI models can learn to express uncertainty, moving beyond confidence scores
This essay introduces the concept of an AI model expressing uncertainty, moving beyond simple confidence scores. It proposes three mechanisms for achieving this: Monte Carlo Dropout, Deep Ensembles, and Out-of-Distribut…
-
New Bayesian Deep Ensemble Method Enhances Predictive Regression
Researchers have developed a new Bayesian deep ensemble method for predictive regression that enhances interpretability and maintains strong predictive performance. This approach combines Bayesian inference with deep en…
-
New CLEAR method improves AI uncertainty quantification by balancing risks
Researchers have introduced CLEAR, a novel calibration method designed to improve predictive interval coverage by addressing both aleatoric and epistemic uncertainty in regression tasks. This method utilizes two distinc…
-
New deep learning model classifies astronomical transients without human labels
Researchers have developed a novel deep learning framework for classifying astronomical transients as real or bogus without requiring human-labeled data. This method utilizes injected simulated transients and a contamin…
-
Deep ensembles outperform late-fusion in multimodal classification
A new research paper proposes using deep ensembles of unimodal neural networks for multimodal classification, challenging traditional late-fusion approaches. The study demonstrates that these ensembles consistently outp…
-
Deep Ensembles Show Linear Mode Connectivity Under Data Shifts
Researchers have investigated the phenomenon of linear mode connectivity (LMC) in deep learning, particularly how it is affected by data shifts in ensembles of image classifiers. The study suggests that data shifts can …
-
Deep learning models evaluated for machinery fault diagnosis with uncertainty
A new research paper published on arXiv explores the effectiveness of various deep learning models in diagnosing faults in rotating machinery, specifically focusing on their ability to handle uncertainty. The study comp…
-
Conformal prediction offers new uncertainty guarantees for physics simulations
Researchers have introduced a novel application of split conformal prediction to neural operator-based physics simulations, offering distribution-free prediction intervals with formal coverage guarantees. This method, a…
-
Deep ensembles fail to capture uncertainty in graph neural networks
A new research paper questions the effectiveness of deep ensembles for uncertainty quantification in graph neural networks. The study found that ensembles offer minimal improvement over single models, with gains primari…
-
New framework unifies uncertainty-aware explainable AI
Researchers have introduced a new framework for explainable AI (XAI) that incorporates uncertainty awareness, moving beyond deterministic attribution maps. This approach formalizes the 'explanation distribution' derived…
-
Research paper distinguishes cross-validation from deep ensembles for AI uncertainty
A new research paper titled "Lost in the Folds" highlights a common misunderstanding in AI research regarding uncertainty estimation in medical image segmentation. The study reveals that using K-fold cross-validation (C…
-
AI models show improved blood pressure estimation reliability
Researchers investigated the reliability of uncertainty quantification in deep learning models for blood pressure estimation from photoplethysmography (PPG) signals. The study found that deep ensembles (DE) offer greate…
-
Singular Bayesian Neural Networks
Researchers have introduced Singular Bayesian Neural Networks, a novel approach that significantly reduces the parameter count required for Bayesian neural networks. By parameterizing weights using a low-rank decomposit…