Exercise 5.4

Answers

(a): It’s not correct to use the perceptron’s VC dimension for the generalization error. Because one has looked the data before selecting the perceptron model, so the actual hypothesis set is much larger than perceptron model.
(b): We don’t know the $d_{V C}$ for the learning model that we actually used. As stated in problem (a), we started from a pretty big hypothesis which might include all models we are aware of. The $d_{V C}$ is not known for such a hypothesis set.

niuers

2021-12-08 09:34