Bayesian Neural Networks
PulseAugur coverage of Bayesian Neural Networks — every cluster mentioning Bayesian Neural Networks across labs, papers, and developer communities, ranked by signal.
6 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…
-
AI advances photonic component design with neurosymbolic and BNN approaches
Researchers have developed new methods for designing photonic components using AI. One approach, "Constrained Co-Design for Photonic Bayesian Neural Networks," focuses on improving the uncertainty estimation of Bayesian…
-
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…
-
Student's t-distribution outperforms Gaussian in Bayesian Neural Networks
Researchers have explored the impact of different likelihood distributions on the performance of Bayesian Neural Networks (BNNs). While Gaussian distributions are commonly used for modeling uncertainty in BNNs due to co…
-
Neural network generalization near interpolation analyzed via statistical mechanics · 2 sources tracked
Two new arXiv papers explore the behavior of shallow neural networks with extensive width, focusing on their generalization capabilities near the interpolation threshold. The research analyzes these networks using stati…
-
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…
-
New SCROLL method optimizes Bayesian neural networks via Bethe free energy
Researchers have developed a new method for training Bayesian neural networks called SCROLL (Shared-Cavity fRee-rOuting Last-Layer). This approach optimizes the Bethe free energy rather than the typical evidence lower b…
-
New Bayesian deep learning method enhances explainability and model compression
Researchers have introduced a novel approach called input-skip Latent Binary Bayesian Neural Networks (ISLaB) to enhance explainability and reduce complexity in deep learning models. This method allows covariates to ski…
-
Bayesian Neural Networks: Infinite Width Matches Polynomial Width Learnability
Researchers have published a paper detailing a width-robust learnability theorem for mean-field Bayesian neural networks. The study establishes that for Boolean-cube targets, learnability at infinite width is equivalent…
-
New BiLoc framework uses 1-bit LiDAR for efficient autonomous localization
Researchers have developed BiLoc, a novel binary neural network framework for 6-DoF LiDAR localization, designed to be computationally efficient for autonomous systems. This approach reinterprets BNN training through th…
-
Bayesian Neural Networks leverage symmetry for improved deep learning performance
Researchers have explored the role of symmetries in deep learning, particularly in Bayesian Neural Networks (BNNs). They investigated whether imposing symmetry constraints on network architecture or learning them throug…
-
New B-PINN framework enhances uncertainty quantification for material degradation prognostics
Researchers have developed a new Bayesian Physics-Informed Neural Network (B-PINN) framework designed to improve uncertainty quantification in prognostics and health management (PHM). This novel approach jointly models …
-
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…
-
New TreeGRNG offers efficient probabilistic AI hardware
Researchers have developed TreeGRNG, a novel binary tree Gaussian random number generator designed for efficient probabilistic AI hardware. This innovation addresses the significant power and computational demands of tr…
-
New Method Disentangles Aleatoric and Epistemic Uncertainties in Neural Networks
Researchers have developed a novel method to disentangle aleatoric and epistemic uncertainties in neural networks. By cooperatively training a variance estimation network with a Bayesian neural network, the proposed app…
-
New SIKA-GP Method Accelerates Gaussian Process Inference for Deep Learning
Researchers have developed SIKA-GP, a novel method to accelerate Gaussian Process (GP) inference for Bayesian Deep Learning. By employing sparse inducing kernel approximations with a dyadic ordered template basis, SIKA-…
-
New method enhances neural network uncertainty estimation
Researchers have developed a new method to improve uncertainty estimation in neural networks by integrating a Dirichlet-based framework with Monte Carlo Dropout. This approach aims to provide more informative uncertaint…
-
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…
-
Federated Martingale Posterior sampling improves Bayesian neural networks
Researchers have introduced Federated Martingale Posterior (FMP) sampling, a novel protocol for federated Bayesian neural networks. This method addresses the difficulty of specifying priors in large models by using a pr…
-
New theory explores Bayesian Neural Networks with dependent weights
Researchers have developed a new theoretical framework for understanding Bayesian Neural Networks (BNNs) with dependent weights. This work extends previous findings by analyzing the posterior distribution of BNN outputs…