Polson, Nicholas G.; Sokolov, Vadim Deep learning: a Bayesian perspective. (English) Zbl 1386.68139 Bayesian Anal. 12, No. 4, 1275-1304 (2017). Summary: 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. Cited in 18 Documents MSC: 68T05 Learning and adaptive systems in artificial intelligence 62F15 Bayesian inference Keywords:deep learning; machine learning; artificial intelligence; LSTM models; prediction; Bayesian hierarchical models; pattern matching; tensorflow Software:BASS; TensorFlow; XGBoost × Cite Format Result Cite Review PDF Full Text: DOI arXiv Euclid