You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
There is a subtle difference between "there exists" and "for all" in the definitions that this problem is getting at.
In particular, $m_{\mathcal H}=2^N$ implies that there exists at least one dataset $X$ of size $N$ that can be shattered. This does not imply that every dataset of size $N$ will be shattered, and so we cannot guarantee that $X$ will be shattered. It is in fact common to have hypothesis classes that can only shatter some datasets of a particular size.
Can someone explain to me why question 14 in the quiz practice questions for wednesday is false? If MhN = 2^N, shouldn't H shatter X?
The text was updated successfully, but these errors were encountered: