Page 144: (a) From Figure 4.12, is initially decreasing. How can this be, if  is increasing in for each ? Because is the hypothesis with smallest among hypotheses, and we have already known that is close to  for small and large , hence the initial decrease. As we set out more data for validating, we [...]

Page 142: Referring to Figure 4.10, why are both curves increasing with ? Why do they converge to each other with increasing ? For the first question, as we use more data to validate, we use less data to train. Less data to train will output worse final hypothesis, hence the increase of both curves. [...]

Page 142: Is an unbiased estimate for the out-of-sample error ? Yes, it is. Because (“unbiased estimate” and “biased estimate” are statistics’ definitions).

Page 133: We have seen both the hard-order constraint and the soft-order constraint. Which do you expect to be more useful for binary classification using the perceptron model? Onwait for a reply here. After the first post, I think I will choose the soft-order constraint with some regularizer that can actually constrain the model (I’m wondering [...]

Page 156: In the augmented error minimization with and , assume that is differentiable and use gradient descent to minimize :     Show that the update rule above is the same as     A note here is that by page 131, we know that: .

Page 131: A more general soft constraint is the Tikhonov regularization constraint     which can capture relationships among the (the matrix is the Tikhonov regularizer). (a) What should be to obtain the constraint ? I think in this case. (b) What should be to obtain the constraint ? is a matrix with first components of [...]

Page 139: Fix (learned from ) and define . We consider how depends on . Let     be the pointwise variance in the out-of-sample error of . (a) Show that . We have: Because each is independent from each other, so: Reference: Properties of variance and covariance. (b) In a classification problem, where , express [...]