Let the components of random vector x be conditionally independent given the class, and ternary valued (1, 0, or -1), with pij = P(xi = 1|wj), qij = P(xi = 0|wj) and rij = P(xi = -1|wj). Show (by deriving) that the Bayes classifier can be represented by quadratic discriminant functions.
Get Answers For Free
Most questions answered within 1 hours.