Bayesian neural networks via MCMC: a Python-based tutorial

arXiv:2304.02595v2 Announce Type: replace-cross
Abstract: Bayesian inference provides a methodology for parameter estimation and uncertainty quantification in machine learning and deep learning methods. Variational inference and Markov Chain Monte-Carlo (MCMC) sampling methods are used to implement Bayesian inference. In the past three decades, MCMC sampling methods have faced some challenges in being adapted to larger models (such as in deep learning) and big data problems. Advanced proposal distributions that incorporate gradients, such as a Langevin proposal distribution, provide a means …

abstract arxiv bayesian bayesian inference challenges cs.ai cs.lg deep learning inference machine machine learning markov mcmc methodology monte-carlo networks neural networks python quantification sampling stat.co stat.ml tutorial type uncertainty via