LFD Book Forum

LFD Book Forum (http://book.caltech.edu/bookforum/index.php)
-   Chapter 2 - Training versus Testing (http://book.caltech.edu/bookforum/forumdisplay.php?f=109)
-   -   Problem 2.16 (http://book.caltech.edu/bookforum/showthread.php?t=4593)

NewtoML 03-12-2015 11:26 AM

Problem 2.16

1. I'm trying to solve Problem 2.16, but somewhat confused by the notation. Does the "c" subscript in "hc" refer to the hypothesis number? If so, can I assume that c is a positive integer c= 0,1,2,3 etc? If not, what is c, and c subscript i? (I couldn't find any subscripts used in this way in the chapters of the book.)

2. I can solve 2.16 by showing that this is equivalent to a perceptron in d dimensions, with d=1, and then using the techniques used in your (excellent) video lecture to show that the VC dimension is exactly d+1. However, is there a simpler way to answer the question?

Thank you!

htlin 03-14-2015 09:18 AM

Re: Problem 2.16
\mathbf{c} is the vector whose components are c_i so each \mathbf{c} vector serves as an index to a hypothesis.

Mimicking the proof for the VC dimension of perceptrons sound like a plausible way of conquering the problem. Hope this helps.

NewtoML 03-14-2015 12:31 PM

Re: Problem 2.16
It does. Thank you very much for responding!

All times are GMT -7. The time now is 04:02 AM.

Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2020, 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.