Originally posted on TowardsDataScience. Table of Contents Preamble Neural Network Generalization Back to Basics: The Bayesian Approach Frequentists Bayesianists Bayesian Inference and Marginalization How to Use a Posterior in Practice? Maximum A Posteriori Estimation Full Predictive Distribution Approximate Predictive Distribution Bayesian Deep Learning Recent Approaches to Bayesian Deep Learning Back to the Paper Deep Ensembles are BMA Combining Deep Ensembles With Bayesian Neural Networks ...| Joris Baan
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being mo...| arXiv.org