Results 11 to 20 of about 199,039 (272)
Bayesian Deep Reinforcement Learning via Deep Kernel Learning [PDF]
International Journal of Computational Intelligence Systems, 2018 Reinforcement learning (RL) aims to resolve the sequential decision-making under uncertainty problem where an agent needs to interact with an unknown environment with the expectation of optimising the cumulative long-term reward. Many real-world problems
Junyu Xuan +3 more
doaj +2 more sources
Deep Learning and Bayesian Methods [PDF]
EPJ Web of Conferences, 2017 A revolution is underway in which deep neural networks are routinely used to solve diffcult problems such as face recognition and natural language understanding.
Prosper Harrison B.
doaj +2 more sources
Bayesian Compression for Deep Learning [PDF]
, 2017 Compression and computational efficiency in deep learning have become a problem of great significance. In this work, we argue that the most principled and effective way to attack this problem is by adopting a Bayesian point of view, where through ...
Louizos, Christos +2 more
core +5 more sources
A Survey on Bayesian Deep Learning [PDF]
ACM Computing Surveys, 2020 A comprehensive artificial intelligence system needs to not only perceive the environment with different `senses' (e.g., seeing and hearing) but also infer the world's conditional (or even causal) relations and corresponding uncertainty.
Wang, Hao, Yeung, Dit-Yan
core +3 more sources
Deep Bayesian Unsupervised Lifelong Learning [PDF]
Neural Networks, 2022 Lifelong Learning (LL) refers to the ability to continually learn and solve new problems with incremental available information over time while retaining previous knowledge. Much attention has been given lately to Supervised Lifelong Learning (SLL) with a stream of labelled data.
Tingting Zhao +3 more
openaire +4 more sources
Credal Bayesian Deep Learning [PDF]
Transactions on Machine Learning Research, 2023 Uncertainty quantification and robustness to distribution shifts are important goals in machine learning and artificial intelligence. Although Bayesian Neural Networks (BNNs) allow for uncertainty in the predictions to be assessed, different sources of predictive uncertainty cannot be distinguished properly.
Caprio, Michele +6 more
openaire +3 more sources
Tracing Hα Fibrils through Bayesian Deep Learning [PDF]
The Astrophysical Journal Supplement Series, 2021 Abstract We present a new deep-learning method, named FibrilNet, for tracing chromospheric fibrils in Hα images of solar observations. Our method consists of a data preprocessing component that prepares training data from a threshold-based tool, a deep-learning model implemented as a Bayesian convolutional neural network for ...
Haodi Jiang +7 more
openaire +2 more sources
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
Laplace Redux -- Effortless Bayesian Deep Learning
Advances in Neural Information Processing Systems (NeurIPS), 2021 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 ...
Daxberger, E. +5 more
openaire +3 more sources
Amortized Bayesian Model Comparison With Evidential Deep Learning [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2023 Comparing competing mathematical models of complex natural processes is a shared goal among many branches of science. The Bayesian probabilistic framework offers a principled way to perform model comparison and extract useful metrics for guiding decisions.
Radev, Stefan T. +6 more
openaire +3 more sources