#1




HW4, Question 1
For the VC bound, we have a m_H(2N) term. Should this be replaced with (2N)^dvc, or merely N^dvc?
I presume the former, but both give answers around 400,000500,000, so confirmation would be useful. 
#2




Re: HW4, Question 1
The VC Generalization bound is defined in terms of m_H(2N), so that's what I used. Specifically m_H(2N) <= (2N)^dvc + 1, so I substituted the Right hand term for m_H(2N).

#3




Re: HW4, Question 1
I used the bound we derived in lecture 6: sum(i=0 to dvc, of N choose i ). This should yield a tighter bound on e as sum(i=0 to dvc of, N choose i ) <= (2N)^dvc

#4




Re: HW4, Question 1
Quote:
__________________
Where everyone thinks alike, no one thinks very much 
#5




Re: HW4, Question 1
Quote:
Thanks professor. 
Thread Tools  
Display Modes  

