Hands-on Guide to Bayesian Neural Network in Classification
Consider an example where you are trying to classify a car and a bike. If an image of a truck is shown to the network, it ideally should not predict anything. But, because of the softmax function, it assigns a high probability to one of the classes and the network wrongly, though confidently predicts it to be a car. In order to avoid this, we use the Bayesian Neural Network (BNN).