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 2.19 (c) (http://book.caltech.edu/bookforum/showthread.php?t=4776)

RicLouRiv 07-17-2017 06:20 AM

Problem 2.19 (c)
I would appreciate some guidance on Problem 2.19 (c).

Using the result of Part (b), I can write:

m_\mathcal{H}(N) \leq \frac{(eN)^D}{\tilde{d}^{\tilde{d}}d_1^{d_1}\cdots d_k^{d_k}},

where D=\tilde{d}+d_1+\cdots+d_k.

If d_{VC} is the dimension, then:

m_\mathcal{H}(d_{VC}) = 2^{d_{VC}} \leq \frac{(e d_{VC})^D}{\tilde{d}^{\tilde{d}}d_1^{d_1}\cdots d_k^{d_k}}

I'm stuck at this point. I don't have a clever way to deal with that denominator...you'd want to re-write it in terms of an inequality involving D, but i don't see how.

All times are GMT -7. The time now is 06:50 PM.

Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2021, 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.