Results 31 to 40 of about 41,144 (258)
Off-the-shelf deep learning is not enough, and requires parsimony, Bayesianity, and causality
npj Computational Materials, 2021 Deep neural networks (‘deep learning’) have emerged as a technology of choice to tackle problems in speech recognition, computer vision, finance, etc. However, adoption of deep learning in physical domains brings substantial challenges stemming from the ...
Rama K. Vasudevan +3 more
doaj +1 more source
Accelerating Bayesian microseismic event location with deep learning [PDF]
Solid Earth, 2021 We present a series of new open-source deep-learning algorithms to accelerate Bayesian full-waveform point source inversion of microseismic events. Inferring the joint posterior probability distribution of moment tensor components and source location is ...
A. Spurio Mancini +5 more
doaj +1 more source
Bayesian deep learning for affordance segmentation in images
2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 2023 IEEE International Conference on Robotics and Automation (ICRA)
Lorenzo Mur-Labadia +2 more
openaire +4 more sources
A Novel Method of Emergency Situation Evaluation for Deep-Sea Based on Bayesian Network
IEEE Access, 2020 In order to make effective emergency decisions timely, this paper proposes an intelligent emergency situation evaluation method based on the Bayesian network for deep-sea emergency response, which is used to evaluate the deep-sea emergency situation ...
Kun Lang, Dongsen Si, Zhihong Ma
doaj +1 more source
Bayesian Generative Active Deep Learning
CoRR, 2019 Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of problems that can be tackled.
Tran, Toan +3 more
openaire +4 more sources
IEEE Access, 2021 Deep learning has demonstrated high accuracy for 3D object shape error modeling necessary to estimate dimensional and geometric quality defects in multi-station assembly systems (MAS).
Sumit Sinha +2 more
doaj +1 more source
Journal of Modern Power Systems and Clean Energy, 2022 Modern power systems are incorporated with distributed energy sources to be environmental-friendly and cost-effective. However, due to the uncertainties of the system integrated with renewable energy sources, effective strategies need to be adopted to ...
Shiyao Zhang, James J.Q. Yu
doaj +1 more source
Understanding Uncertainty in Bayesian Deep Learning
CoRR, 2021 Neural Linear Models (NLM) are deep Bayesian models that produce predictive uncertainty by learning features from the data and then performing Bayesian linear regression over these features. Despite their popularity, few works have focused on formally evaluating the predictive uncertainties of these models.
openaire +3 more sources
Early Detection of the Advanced Persistent Threat Attack Using Performance Analysis of Deep Learning
IEEE Access, 2020 One of the most common and critical destructive attacks on the victim system is the advanced persistent threat (APT)-attack. An APT attacker can achieve its hostile goal through obtaining information and gaining financial benefits from the infrastructure
Javad Hassannataj Joloudari +5 more
doaj +1 more source
Explicitly Bayesian Regularizations in Deep Learning
CoRR, 2019 Generalization is essential for deep learning. In contrast to previous works claiming that Deep Neural Networks (DNNs) have an implicit regularization implemented by the stochastic gradient descent, we demonstrate explicitly Bayesian regularizations in a specific category of DNNs, i.e., Convolutional Neural Networks (CNNs).
Xinjie Lan, Kenneth E. Barner
openaire +2 more sources