Results 1 to 10 of about 234,090 (282)
Stochastic Control for Bayesian Neural Network Training [PDF]
Entropy, 2022 In this paper, we propose to leverage the Bayesian uncertainty information encoded in parameter distributions to inform the learning procedure for Bayesian models.
Ludwig Winkler +2 more
doaj +2 more sources
Probabilistic Damage Detection of a Steel Truss Bridge Model by Optimally Designed Bayesian Neural Network [PDF]
Sensors, 2018 Excellent pattern matching capability makes artificial neural networks (ANNs) a very promising approach for vibration-based structural health monitoring (SHM). The proper design of the network architecture with the suitable complexity is vital to the ANN-
Tao Yin, Hong-ping Zhu
doaj +2 more sources
Minimax Bayesian Neural Networks
EntropyRobustness is an important issue in deep learning, and Bayesian neural networks (BNNs) provide means of robustness analysis, while the minimax method is a conservative choice in the classical Bayesian field.
Junping Hong, Ercan Engin Kuruoglu
doaj +3 more sources
Bayesian Reasoning with Trained Neural Networks [PDF]
Entropy, 2021 We showed how to use trained neural networks to perform Bayesian reasoning in order to solve tasks outside their initial scope. Deep generative models provide prior knowledge, and classification/regression networks impose constraints. The tasks at hand were formulated as Bayesian inference problems, which we approximately solved through variational or ...
Jakob Knollmüller, Torsten A. Enßlin
openaire +6 more sources
Continual Learning Using Bayesian Neural Networks [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2021 Continual learning models allow to learn and adapt to new changes and tasks over time. However, in continual and sequential learning scenarios in which the models are trained using different data with various distributions, neural networks tend to forget the previously learned knowledge.
Honglin Li +3 more
openaire +5 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.
Charnock, Tom +2 more
openaire +2 more sources
Frontiers in Energy Research, 2022 Knowledge-driven and data-driven methods are the two representative categories of intelligent technologies used in fault diagnosis in nuclear power plants.
Ben Qi +3 more
doaj +1 more source
Energy financial risk early warning model based on Bayesian network
Energy Reports, 2023 Oil is a global, non-renewable energy source, which plays a pivotal role in the development of the global economy and the strategic reserve system. With the expansion of crude oil futures trading scale, crude oil is no longer a pure energy commodity, but
Lin Wei, Hanyue Yu, Bin Li
doaj +1 more source
Доклады Белорусского государственного университета информатики и радиоэлектроники, 2021 At present, neural networks are increasingly used to solve many problems instead of traditional methods for solving them. This involves comparing the neural network and the traditional method for specific tasks.
V. S. Mukha
doaj +1 more source
An Overview of Neural Network Methods for Predicting Uncertainty in Atmospheric Remote Sensing
Remote Sensing, 2021 In this paper, we present neural network methods for predicting uncertainty in atmospheric remote sensing. These include methods for solving the direct and the inverse problem in a Bayesian framework. In the first case, a method based on a neural network
Adrian Doicu +4 more
doaj +1 more source