LFD Book Forum  

Go Back   LFD Book Forum > Book Feedback - Learning From Data > Chapter 2 - Training versus Testing

Reply
 
Thread Tools Display Modes
  #1  
Old 10-19-2016, 05:16 PM
alexd alexd is offline
Junior Member
 
Join Date: Oct 2016
Posts: 1
Default equation 2.13 on page 57

I've been reading the book in parallel with watching the lectures. I think that equation 2.13 on page 57 is wrong or perhaps just misleading. The expression right before equation 2.13 is of the form
N >= const * ln(m(2N)) for fixed eps and delta.
Then equation 2.10, m(N) <= 1+N^d_vc, is used to rewrite the expression as equation 2.13, N >= const * ln(1+(2N)^d_vc)
But all we can really say from these two expressions is
N >= const * ln(m(2N)) <= const * ln(1+(2N)^d_vc)

In other words, I don't see how I can know the sign of the inequality "?" in
N ? const * ln(1+(2N)^d_vc)

What am I missing This seems an important thing, so please help me see my error....
Reply With Quote
Reply

Tags
sample size, vc dimension

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT -7. The time now is 03:44 PM.


Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2017, Jelsoft Enterprises Ltd.
The contents of this forum are to be used ONLY by readers of the Learning From Data book by Yaser S. Abu-Mostafa, Malik Magdon-Ismail, and Hsuan-Tien Lin, and participants in the Learning From Data MOOC by Yaser S. Abu-Mostafa. No part of these contents is to be communicated or made accessible to ANY other person or entity.