Queensland's institutional digital repository (The University of Queensland) · 2019 · 26 citations · 14 references
ComputingComputer ScienceForecastingMachine LearningStatistical LearningBayesian InferenceBayesian LearningBayesian StatisticsGaussian ProcessesNeural NetworksReinforcement LearningBayesian NetworksBayesian Neural NetworksEliciting Prior KnowledgeKernel LearningPrior Related KnowledgeSeasonal Variation
A simple, flexible approach to creating expressive priors in Gaussian process (GP) models makes new kernels from a combination of basic kernels, e.g. summing a periodic and linear kernel can capture seasonal variation with a long term trend. Despite a well-studied link between GPs and Bayesian neural networks (BNNs), the BNN analogue of this has not yet been explored. This paper derives BNN architectures mirroring such kernel combinations. Furthermore, it shows how BNNs can produce periodic kernels, which are often useful in this context. These ideas provide a principled approach to designing BNNs that incorporate prior knowledge about a function. We showcase the practical value of these ideas with illustrative experiments in supervised and reinforcement learning settings.
14
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Sparse Gaussian Processes using Pseudo-inputs
Edward Snelson, Zoubin Ghahramani · 2005 · 1.3K citations
Weight Uncertainty in Neural Networks
Charles Blundell, Julien Cornebise, Koray Kavukcuoglu et al. · arXiv (Cornell University) · 2015 · 1.3K citations · Full text
Deep Bayesian Active Learning with Image Data
Yarin Gal, Riashat Islam, Zoubin Ghahramani · arXiv (Cornell University) · 2017 · 580 citations · Full text