Results 31 to 40 of about 4,609,632 (195)

Comparative Study of Various Neural Network Types for Direct Inverse Material Parameter Identification in Numerical Simulations

open access: yesApplied Sciences, 2022
Increasing product requirements in the mechanical engineering industry and efforts to reduce time-to-market demand highly accurate and resource-efficient finite element simulations.
Paul Meißner, Tom Hoppe, Thomas Vietor
doaj   +1 more source

On Sequential Bayesian Inference for Continual Learning

open access: yesEntropy, 2023
Sequential Bayesian inference can be used for continual learning to prevent catastrophic forgetting of past tasks and provide an informative prior when learning new tasks.
Samuel Kessler   +4 more
doaj   +1 more source

Computational inference of neural information flow networks [PDF]

open access: yes, 2006
This research was supported by a Packard Foundation grant and a US National Science Foundation (NSF) Waterman Award to EDJ, an NSF CAREER grant and an Alfred P.
Tom V. Smulders   +21 more
core   +2 more sources

Bayesian Neural Networks for Aroma Classification [PDF]

open access: yesJournal of Chemical Information and Computer Sciences, 2002
Bayesian Neural Networks (BNNs) are investigated to test their potential to distinguish between different aroma impressions. Special attention is thereby drawn on mixed aroma impressions, resulting from the flavor description of a single compound with more than one aroma quality.
Klocker, Johanna   +3 more
openaire   +4 more sources

Neural networks using Bayesian training [PDF]

open access: yes, 2003
summary:Bayesian probability theory provides a framework for data modeling. In this framework it is possible to find models that are well-matched to the data, and to use these models to make nearly optimal predictions.
Levický, Miroslav   +1 more
core   +1 more source

Simple Direct Uncertainty Quantification Technique Based on Machine Learning Regression

open access: yesProceedings of the International Florida Artificial Intelligence Research Society Conference, 2022
Epistemic uncertainty quantification provides useful insight into both deep and shallow neural networks' understanding of the relationships between their training distributions and unseen instances and can serve as an estimate of classification ...
Katherine E. Brown, Douglas A. Talbert
doaj   +1 more source

Prediction of concrete fatigue durability using Bayesian neural networks

open access: yesComputer Assisted Methods in Engineering and Science, 2022
The utility of Bayesian neural networks to predict concrete fatigue durability as a function of concrete mechanical parameters of a specimen and characteristics of the loading cycle is investigated.
Marek Słoński
doaj  

Bayesian Neural Network Ensembles

open access: yesCoRR, 2018
Ensembles of neural networks (NNs) have long been used to estimate predictive uncertainty; a small number of NNs are trained from different initialisations and sometimes on differing versions of the dataset. The variance of the ensemble's predictions is interpreted as its epistemic uncertainty.
Tim Pearce, Mohamed Zaki, Andy Neely
openaire   +2 more sources

Bayesian Neural Networks: Essentials

open access: yesCoRR, 2021
Bayesian neural networks utilize probabilistic layers that capture uncertainty over weights and activations, and are trained using Bayesian inference. Since these probabilistic layers are designed to be drop-in replacement of their deterministic counter parts, Bayesian neural networks provide a direct and natural way to extend conventional deep neural ...
openaire   +2 more sources

Bayesian Neural Networks for Sparse Coding [PDF]

open access: yesICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
Deep learning is actively used in the area of sparse coding. In current deep sparse coding methods uncertainty of predictions is rarely estimated, thus providing the results that lack the quantitative justification. Bayesian learning provides the way to estimate the uncertainty of predictions in neural networks (NNs) by imposing the prior distributions
Danil Kuzin   +2 more
openaire   +2 more sources

Home - About - Disclaimer - Privacy