�ݺ�ߣ

1. Bayesian methods can be used to approximate the probability of B given A (P(B|A)) by treating it as a function (f(A;w)) of the exemplars A and weights w, based on training data of examples of A and B. 2. A Bayesian approach involves placing prior probabilities on the model parameters (weights) to avoid overfitting, and computing the posterior distribution over the weights given the data. 3. Key aspects of Bayesian methods include choosing a model shape (e.g. linear or sigmoid function), placing independent precision tuners on the weights and basis functions to control complexity, and interpreting the confidence levels of the unknown weights.Read less