%0 Report %1 jospin2020handson %A Jospin, Laurent Valentin %A Buntine, Wray %A Boussaid, Farid %A Laga, Hamid %A Bennamoun, Mohammed %D 2020 %K bayesian deeplearning dnn network neural tutorial %T Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users %U http://arxiv.org/abs/2007.06823 %X Modern deep learning methods have equipped researchers and engineers with incredibly powerful tools to tackle problems that previously seemed impossible. However, since deep learning methods operate as black boxes, the uncertainty associated with their predictions is often challenging to quantify. Bayesian statistics offer a formalism to understand and quantify the uncertainty associated with deep neural networks predictions. This paper provides a tutorial for researchers and scientists who are using machine learning, especially deep learning, with an overview of the relevant literature and a complete toolset to design, implement, train, use and evaluate Bayesian neural networks.

@techreport{jospin2020handson, abstract = {Modern deep learning methods have equipped researchers and engineers with incredibly powerful tools to tackle problems that previously seemed impossible. However, since deep learning methods operate as black boxes, the uncertainty associated with their predictions is often challenging to quantify. Bayesian statistics offer a formalism to understand and quantify the uncertainty associated with deep neural networks predictions. This paper provides a tutorial for researchers and scientists who are using machine learning, especially deep learning, with an overview of the relevant literature and a complete toolset to design, implement, train, use and evaluate Bayesian neural networks.}, added-at = {2021-06-18T11:25:22.000+0200}, author = {Jospin, Laurent Valentin and Buntine, Wray and Boussaid, Farid and Laga, Hamid and Bennamoun, Mohammed}, biburl = {https://www.bibsonomy.org/bibtex/27b9eee5d243cdca64efc5100e9eefe1f/jaeschke}, description = {[2007.06823] Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users https://arxiv.org/abs/2007.06823}, interhash = {3b1c04a3fbbdba25f7daa38de6941aad}, intrahash = {7b9eee5d243cdca64efc5100e9eefe1f}, keywords = {bayesian deeplearning dnn network neural tutorial}, note = {cite arxiv:2007.06823Comment: 35 pages, 15 figures}, timestamp = {2021-06-18T11:25:22.000+0200}, title = {Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users}, url = {http://arxiv.org/abs/2007.06823}, year = 2020 }