Are Neural Networks Bayesian?

A Bayesian neural network (BNN) refers to extending standard networks with posterior inference. Standard NN training via optimization is (from a probabilistic perspective) equivalent to maximum likelihood estimation (MLE) for the weights. ... Using MLE ignores any uncertainty that we may have in the proper weight values.

Is a neural network a Bayesian network?

Classical neural networks use maximum likelihood to determine network parameters (weights and biases) and hence make predictions. ... A Bayesian network is a graphical model that encodes probabilistic relationships among variables of interest.

What are Bayesian neural networks good for?

Bayesian neural nets are useful for solving problems in domains where data is scarce, as a way to prevent overfitting. Example applications are molecular biology and medical diagnosis (areas where data often come from costly and difficult experimental work).