Deep learning: a Bayesian perspective
From MaRDI portal
Abstract: Deep learning is a form of machine learning for nonlinear high dimensional pattern matching and prediction. By taking a Bayesian probabilistic perspective, we provide a number of insights into more efficient algorithms for optimisation and hyper-parameter tuning. Traditional high-dimensional data reduction techniques, such as principal component analysis (PCA), partial least squares (PLS), reduced rank regression (RRR), projection pursuit regression (PPR) are all shown to be shallow learners. Their deep learning counterparts exploit multiple deep layers of data reduction which provide predictive performance gains. Stochastic gradient descent (SGD) training optimisation and Dropout (DO) regularization provide estimation and variable selection. Bayesian regularization is central to finding weights and connections in networks to optimize the predictive bias-variance trade-off. To illustrate our methodology, we provide an analysis of international bookings on Airbnb. Finally, we conclude with directions for future research.
Recommendations
Cited in
(31)- Detecting conflicting summary statistics in likelihood-free inference
- Bayesian distillation of deep learning models
- Challenges in Markov chain Monte Carlo for Bayesian neural networks
- Comparison of deep neural networks and deep hierarchical models for spatio-temporal data
- Uncertainty quantification in scientific machine learning: methods, metrics, and comparisons
- Bayesian Deep Net GLM and GLMM
- Learning Summary Statistic for Approximate Bayesian Computation via Deep Neural Network
- scientific article; zbMATH DE number 7626754 (Why is no real title available?)
- Marginally Calibrated Deep Distributional Regression
- Computer model calibration with time series data using deep learning and quantile regression
- Understanding Deep Learning with Statistical Relevance
- Deep learning: a statistical viewpoint
- Weighted Bayesian bootstrap for scalable posterior distributions
- Marginally calibrated response distributions for end-to-end learning in autonomous driving
- Bayesian quickest detection of credit card fraud
- Informative Bayesian neural network priors for weak signals
- Data augmentation for Bayesian deep learning
- Multimodel ensemble analysis with neural network Gaussian processes
- Deep learning from a statistical perspective
- Deep learning for spatio-temporal modeling: dynamic traffic flows and high frequency trading
- Deep learning for energy markets
- Deep learning: computational aspects
- Copula deep learning control chart for multivariate zero inflated count response variables
- Industrial Forecasting with Exponentially Smoothed Recurrent Neural Networks
- The application of Bayesian inference under SAFE model
- Bayesian deep learning with multilevel trace-class neural networks
- Fitting deep neural networks into the statistical regression modelling setting
- On the effectiveness of partially deterministic Bayesian neural networks
- Shedding light on uncertainties in machine learning: formal derivation and optimal model selection
- Minimization by incremental stochastic surrogate optimization for large scale nonconvex problems
- Fusing climate data products using a spatially varying autoencoder
This page was built for publication: Deep learning: a Bayesian perspective
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1699718)
