Results 41 to 50 of about 9,807,419 (288)
Subspace Inference for Bayesian Deep Learning
Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Bayesian inference techniques to deep neural networks is challenging due to the high dimensionality of the parameter space.
Pavel Izmailov +5 more
openaire +4 more sources
Explicitly Bayesian Regularizations in Deep Learning
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
Bayesian deep learning for affordance segmentation in images
2023 IEEE International Conference on Robotics and Automation (ICRA)
Lorenzo Mur-Labadia +2 more
openaire +4 more sources
Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis
Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular.
Chernoded Andrey +3 more
doaj +1 more source
Probabilistic hydrological forecasting based on variational Bayesian deep learning
The field of deep learning research in hydrology primarily aims to enhance prediction capabilities. However, the intricate structure of deep learning models often leads to predictions that are difficult to explain and trust, making the development of ...
Dayang LI +4 more
doaj +1 more source
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
Laplace Redux -- Effortless Bayesian Deep Learning
Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty quantification and model selection. The Laplace approximation (LA) is a classic, and arguably the simplest family of approximations for the intractable posteriors of deep ...
Erik A. Daxberger +5 more
openaire +5 more sources
Episode-based active learning with Bayesian neural networks [PDF]
We investigate different strategies for active learning with Bayesian deep neural networks. We focus our analysis on scenarios where new, unlabeled data is obtained episodically, such as commonly encountered in mobile robotics applications. An evaluation
Sunderhauf, N. +8 more
core +1 more source
Reconstructing enzyme evolution by protein engineering
Natural enzyme evolution can be retraced by protein engineering methods such as directed evolution, rational design, and ancestral sequence reconstruction. These approaches reveal how enzymes emerged from ligand‐binding scaffolds, developed varying substrate preferences, formed oligomeric complexes, adapted to environmental changes, and evolved novel ...
Lukas Drexler +2 more
wiley +1 more source
Bayesian Sparsification for Deep Neural Networks With Bayesian Model Reduction
Deep learning’s immense capabilities are often constrained by the complexity of its models, leading to an increasing demand for effective sparsification techniques.
Dimitrije Markovic +2 more
doaj +1 more source

