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 03-25-2012, 12:25 AM
yaser's Avatar
yaser yaser is offline
Caltech
 
Join Date: Aug 2009
Location: Pasadena, California, USA
Posts: 1,474
Default Exercises and Problems

Please comment on the chapter problems in terms of difficulty, clarity, and time demands. This information will help us and other instructors in choosing problems to assign in our classes.

Also, please comment on the exercises in terms of how useful they are in understanding the material.
__________________
Where everyone thinks alike, no one thinks very much
Reply With Quote
  #2  
Old 07-02-2012, 02:36 PM
tadworthington tadworthington is offline
Member
 
Join Date: Jun 2012
Location: Chicago, IL
Posts: 32
Default ERRATA: Small mistake in description of Exercise 2.1

I won't "mathify" this correction, as I don't know how in this forum (my LaTex has escaped me after years of neglect!). It's a minor point, but I feel like it should be corrected. In the wording for Exercise 2.1 on page 45:

ERROR: "Verify that m_H(n) < 2^k"
CORRECTION: "Verify that m_H(k) < 2^k"

Thanks!
Reply With Quote
  #3  
Old 07-02-2012, 03:58 PM
yaser's Avatar
yaser yaser is offline
Caltech
 
Join Date: Aug 2009
Location: Pasadena, California, USA
Posts: 1,474
Default Re: ERRATA: Small mistake in description of Exercise 2.1

Quote:
Originally Posted by tadworthington View Post
I won't "mathify" this correction, as I don't know how in this forum (my LaTex has escaped me after years of neglect!). It's a minor point, but I feel like it should be corrected. In the wording for Exercise 2.1 on page 45:

ERROR: "Verify that m_H(n) < 2^k"
CORRECTION: "Verify that m_H(k) < 2^k"

Thanks!
Thank you for catching this!
__________________
Where everyone thinks alike, no one thinks very much
Reply With Quote
  #4  
Old 08-24-2012, 09:20 AM
vsthakur vsthakur is offline
Member
 
Join Date: Jun 2012
Posts: 14
Default Problem 2.9 : Growth function of perceptron, seems incorrect

The problem says that in case of perceptron in d-dimensional space, growth function is equal to B(N,k). Consider the following case :

d = 2, implies dvc = 2+1 = 3
N = 4
B(N,k) = 15
but the maximum no. of dichotomies possible in this case is only 14

Can someone please comment if i am missing something.

Thanks.

Vishwajeet.
Reply With Quote
  #5  
Old 08-24-2012, 01:17 PM
magdon's Avatar
magdon magdon is offline
RPI
 
Join Date: Aug 2009
Location: Troy, NY, USA.
Posts: 592
Default Re: Problem 2.9 : Growth function of perceptron, seems incorrect

Thanks for catching this erratum. The problem shows the upper bound based on the VC dimension. The actual growth function is given by:

2\sum_{i=0}^d \left({N-1}\atop i\right).

Our appologies.

Quote:
Originally Posted by vsthakur View Post
The problem says that in case of perceptron in d-dimensional space, growth function is equal to B(N,k). Consider the following case :

d = 2, implies dvc = 2+1 = 3
N = 4
B(N,k) = 15
but the maximum no. of dichotomies possible in this case is only 14

Can someone please comment if i am missing something.

Thanks.

Vishwajeet.
__________________
Have faith in probability
Reply With Quote
  #6  
Old 08-25-2012, 09:04 PM
vsthakur vsthakur is offline
Member
 
Join Date: Jun 2012
Posts: 14
Default Re: Problem 2.9 : Growth function of perceptron, seems incorrect

Thank you
Reply With Quote
  #7  
Old 08-29-2012, 02:39 AM
vsthakur vsthakur is offline
Member
 
Join Date: Jun 2012
Posts: 14
Default Re: Problem 2.9 : Growth function of perceptron, seems incorrect

Sorry for the delayed response here, but i still find that

m_{H}(N) = 2 \sum_{i=0}^d \left({N-1}\atop i\right)

is not the case for a perceptron in d-dimensional space.

When N=6 and d=2, this equation says m_{H}(n) = 32, while i was able to get 38 dichotomies (by picking 6 equidistant points on the circumference of a circle).

If i am missing something, then can you please point me to the proof.

Thank you.
Reply With Quote
  #8  
Old 08-29-2012, 03:10 AM
vsthakur vsthakur is offline
Member
 
Join Date: Jun 2012
Posts: 14
Default Problem 2.10

To prove : m_H(2N) \le m_H(N)^2

As this is a generic statement, it has to apply to every growth function. But all we know about the growth functions (in general) is their bound, in terms of N and d_{vc}.

Also, we know that if N \le d_{vc} then m_H(N) is an increasing function whose value is 2^N. But, if N > d_{vc}, then we can only say that m_H(N) is non-decreasing and is bounded by N^{d_{vc}} + 1.

I guess my question is that how can we prove the generic statement above. Kindly shed some light on the proof strategy.

Thank you,

Vishwajeet.
Reply With Quote
  #9  
Old 08-29-2012, 07:46 AM
vsthakur vsthakur is offline
Member
 
Join Date: Jun 2012
Posts: 14
Default Possible correction to Problem 2.14 (b)

The problem says,

(b) Suppose that l satisfies 2^l  > K l^{d_{vc}+1}. Show that d_{vc}(H) \le l.

I suppose it should say,

(b) Suppose that l satisfies 2^l  > l^{K(d_{vc}+1)}. Show that d_{vc}(H) \le l.

If this is indeed the case, then can you please clarify part (c) as well.

Thank you,

Vishwajeet.
Reply With Quote
  #10  
Old 08-29-2012, 09:30 AM
magdon's Avatar
magdon magdon is offline
RPI
 
Join Date: Aug 2009
Location: Troy, NY, USA.
Posts: 592
Default Re: Possible correction to Problem 2.14 (b)

The problem, though an over-estimate seems correct.

Hint: If you have \ell points, then {\cal H}_1 can implement at most \ell^{d_{VC}}+1\le\ell^{d_{VC}+1} dichotomies on those points. Now try to upper bound the number of dichotomies that all K hypothesis sets can implement on these \ell points and proceed from there.

Quote:
Originally Posted by vsthakur View Post
The problem says,

(b) Suppose that l satisfies 2^l  > K l^{d_{vc}+1}. Show that d_{vc}(H) \le l.

I suppose it should say,

(b) Suppose that l satisfies 2^l  > l^{K(d_{vc}+1)}. Show that d_{vc}(H) \le l.

If this is indeed the case, then can you please clarify part (c) as well.

Thank you,

Vishwajeet.
__________________
Have faith in probability
Reply With Quote
Reply

Tags
errata, growth function, perceptron

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 08:45 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.