Results 11 to 20 of about 3,905,952 (289)
Efficient Scaling of Bayesian Neural Networks
IEEE AccessWhile Bayesian neural networks (BNNs) have gained popularity for their theoretical guarantees and robustness, they have yet to see a convincing implementation at scale.
Jacob R. Epifano +3 more
doaj +2 more sources
Bayesian Neural Networks [PDF]
, 2022 In recent times, neural networks have become a powerful tool for the analysis of complex and abstract data models. However, their introduction intrinsically increases our uncertainty about which features of the analysis are model-related and which are due to the neural network.
Tom Charnock +2 more
openaire +3 more sources
Neural Bayesian Network Understudy
CoRR, 2022 Bayesian Networks may be appealing for clinical decision-making due to their inclusion of causal knowledge, but their practical adoption remains limited as a result of their inability to deal with unstructured data. While neural networks do not have this limitation, they are not interpretable and are inherently unable to deal with causal structure in ...
Rabaey, Paloma +2 more
openaire +4 more sources
Artificial neural networks compared with Bayesian generalized linear regression for leaf rust resistance prediction in Arabica coffee [PDF]
Pesquisa Agropecuária Brasileira, 2017 : The objective of this work was to evaluate the use of artificial neural networks in comparison with Bayesian generalized linear regression to predict leaf rust resistance in Arabica coffee (Coffea arabica).
Gabi Nunes Silva +9 more
doaj +2 more sources
Prediction of silicon content in the hot metal using Bayesian networks and probabilistic reasoning
IJAIN (International Journal of Advances in Intelligent Informatics), 2021 The blast furnace is the principal method of producing cast iron. In the production of cast iron, the control of silicon is vital because this impurity is harmful to almost all steels.
Wandercleiton Cardoso, Renzo di Felice
doaj +1 more source
Explaining Bayesian Neural Networks
CoRR, 2021 To advance the transparency of learning machines such as Deep Neural Networks (DNNs), the field of Explainable AI (XAI) was established to provide interpretations of DNNs' predictions. While different explanation techniques exist, a popular approach is given in the form of attribution maps, which illustrate, given a particular data point, the relevant ...
Kirill Bykov +6 more
openaire +3 more sources
Differentiable PAC–Bayes Objectives with Partially Aggregated Neural Networks
Entropy, 2021 We make two related contributions motivated by the challenge of training stochastic neural networks, particularly in a PAC–Bayesian setting: (1) we show how averaging over an ensemble of stochastic neural networks enables a new class of partially ...
Felix Biggs, Benjamin Guedj
doaj +1 more source
G3: Genes, Genomes, Genetics, 2021 In conventional linear models for whole-genome prediction and genome-wide association studies (GWAS), it is usually assumed that the relationship between genotypes and phenotypes is linear.
Tianjing Zhao, Rohan Fernando, Hao Cheng
doaj +1 more source
CoRR, 2018 This paper describes and discusses Bayesian Neural Network (BNN). The paper showcases a few different applications of them for classification and regression problems. BNNs are comprised of a Probabilistic Model and a Neural Network. The intent of such a design is to combine the strengths of Neural Networks and Stochastic modeling.
Vikram Mullachery +2 more
openaire +3 more sources
Scaling Up Bayesian Neural Networks with Neural Networks
Trans. Mach. Learn. Res., 2023 25 ...
Zahra Moslemi +3 more
openaire +3 more sources