Results 21 to 30 of about 41,144 (258)
Deep-learning jets with uncertainties and more
SciPost Physics, 2020 Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main features of Bayesian versions of established deep-learning taggers.
Sven Bollweg, Manuel Haussmann, Gregor Kasieczka, Michel Luchmann, Tilman Plehn, Jennifer Thompson
doaj +1 more source
BayesDLL: Bayesian Deep Learning Library
CoRR, 2023 We release a new Bayesian neural network library for PyTorch for large-scale deep networks. Our library implements mainstream approximate Bayesian inference algorithms: variational inference, MC-dropout, stochastic-gradient MCMC, and Laplace approximation. The main differences from other existing Bayesian neural network libraries are as follows: 1) Our
Minyoung Kim 0001, Timothy M. Hospedales
openaire +2 more sources
Bayesian Compression for Deep Learning
CoRR, 2017 Published as a conference paper at NIPS ...
Louizos, C., Ullrich, K., Welling, M.
openaire +6 more sources
Bayesian Deep Reinforcement Learning Algorithm for Solving Deep Exploration Problems
Jisuanji kexue yu tansuo, 2020 In the field of reinforcement learning, how to balance the relationship between exploration and exploi-tation is a hard problem. The reinforcement learning method proposed in recent years mainly focuses on how to combine the deep learning technology to ...
YANG Min, WANG Jie
doaj +1 more source
Federated Deep Learning with Bayesian Privacy
CoRR, 2021 Federated learning (FL) aims to protect data privacy by cooperatively learning a model without sharing private data among users. For Federated Learning of Deep Neural Network with billions of model parameters, existing privacy-preserving solutions are unsatisfactory.
Hanlin Gu +5 more
openaire +3 more sources
Measuring the Uncertainty of Predictions in Deep Neural Networks with Variational Inference
Sensors, 2020 We present a novel approach for training deep neural networks in a Bayesian way. Compared to other Bayesian deep learning formulations, our approach allows for quantifying the uncertainty in model parameters while only adding very few additional ...
Jan Steinbrener +2 more
doaj +1 more source
Data Augmentation for Bayesian Deep Learning
Bayesian Analysis, 2023 Deep Learning (DL) methods have emerged as one of the most powerful tools for functional approximation and prediction. While the representation properties of DL have been well studied, uncertainty quantification remains challenging and largely unexplored.
Wang, Yuexi +2 more
openaire +2 more sources
A Cache-Enabled Device-to-Device Approach Based on Deep Learning
IEEE Access, 2023 In this paper, we present a deep learning-based Device-to-Device (D2D) approach that utilizes Gated Recurrent Unit (GRU) model that is optimized through Bayesian optimization for hyperparameter tuning. The proposed approach, DLCE-D2D (Deep Learning Cache-
Salma M. Maher +3 more
doaj +1 more source
The Case for Bayesian Deep Learning
CoRR, 2020 The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for deep neural networks. (1) Neural networks are typically underspecified by the data, and can represent many different but high performing models corresponding to different ...
openaire +2 more sources