Consider the following probabilities: PA-olYs0)-04, PA-1 l Y = 0) = 0.6 P(A-OlY-1) = 0.6, P(A-11Y-1) = 0.4 Suppose there is another binary feature B that is perfectly correlated with A when Y 0, but is independent of A when Y 1. For simplicity, assume that the class conditional probabilities for B are the same as for A. You are given an example with A = 0, B = 0, P (Y = O) = P (Y = 1) = 0.5. Compute the posterior probabilities for Y = 0 and Y = 1 using Naive Bayes formulation, and what class will be assigned? What if you consider the perfect correlation between A and B. Does this change your posterior probability calculation and as a result the corresponding class assignment? Show all your work