LFD Book Forum  

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

Reply
 
Thread Tools Display Modes
  #11  
Old 08-29-2012, 12:44 PM
yaser's Avatar
yaser yaser is offline
Caltech
 
Join Date: Aug 2009
Location: Pasadena, California, USA
Posts: 1,474
Default Re: Problem 2.10

Quote:
Originally Posted by vsthakur View Post
But all we know about the growth functions (in general) is their bound
Actually, we also know the definition of growth functions, and this may be the key to answering the question.
__________________
Where everyone thinks alike, no one thinks very much
Reply With Quote
  #12  
Old 08-29-2012, 08:09 PM
htlin's Avatar
htlin htlin is offline
NTU
 
Join Date: Aug 2009
Location: Taipei, Taiwan
Posts: 562
Default Re: Problem 2.9 : Growth function of perceptron, seems incorrect

Quote:
Originally Posted by vsthakur View Post
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.
I checked the case you are describing, and the number of dichotomies in the case is 32. (Hint: did you double-calculate the case of 3-positive and 3-negative?) Hope this helps.
__________________
When one teaches, two learn.
Reply With Quote
  #13  
Old 08-30-2012, 04:45 AM
vsthakur vsthakur is offline
Member
 
Join Date: Jun 2012
Posts: 14
Default Re: Problem 2.9 : Growth function of perceptron, seems incorrect

Quote:
Originally Posted by htlin View Post
I checked the case you are describing, and the number of dichotomies in the case is 32. (Hint: did you double-calculate the case of 3-positive and 3-negative?) Hope this helps.
You are right, that was the mistake. My apologies.
Thank you.
Reply With Quote
  #14  
Old 09-01-2012, 10:34 AM
vsthakur vsthakur is offline
Member
 
Join Date: Jun 2012
Posts: 14
Default Re: Problem 2.10

Quote:
Originally Posted by yaser View Post
Actually, we also know the definition of growth functions, and this may be the key to answering the question.
I think i get it now. Let m_H(N)=k. Now, if we partition any set of 2N points into two sets of N points each, each of these two partitions will produce k dichotomies at best. If we now combine these two sets, then the maximum no. of dichotomies possible will be the cross product of the two sets of dichotomies (with N points each), i.e.,
m_H(2N) \le k^2 = m_h(N)^2

Thank you.
Reply With Quote
  #15  
Old 09-01-2012, 10:46 AM
vsthakur vsthakur is offline
Member
 
Join Date: Jun 2012
Posts: 14
Default Re: Possible correction to Problem 2.14 (b)

Quote:
Originally Posted by magdon View Post
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.
Got it, thanks. The inequality should be strict i think (d_{vc}(H) < l, when \; 2^l > Kl^{d_{vc}+1}).
Reply With Quote
  #16  
Old 09-03-2012, 06:54 AM
magdon's Avatar
magdon magdon is offline
RPI
 
Join Date: Aug 2009
Location: Troy, NY, USA.
Posts: 592
Default Re: Problem 2.10

Yes, well done.

Quote:
Originally Posted by vsthakur View Post
I think i get it now. Let m_H(N)=k. Now, if we partition any set of 2N points into two sets of N points each, each of these two partitions will produce k dichotomies at best. If we now combine these two sets, then the maximum no. of dichotomies possible will be the cross product of the two sets of dichotomies (with N points each), i.e.,
m_H(2N) \le k^2 = m_h(N)^2

Thank you.
__________________
Have faith in probability
Reply With Quote
  #17  
Old 09-22-2012, 03:00 PM
doris doris is offline
Junior Member
 
Join Date: Sep 2012
Posts: 3
Default Problem 2.3 c

the last comment confused me a little bit.
For a given set of N points, we should change the center of the sphere to get as many dichotomies as we can, thus measuring the effective number of hypotheses (spheres) in this hypothesis set.

Does it make sense to move project the spheres from 3D to 1D and look at the problem as intervals of +1 for a<=x<=b and -a>=x>=b?
Reply With Quote
  #18  
Old 09-23-2012, 10:42 AM
magdon's Avatar
magdon magdon is offline
RPI
 
Join Date: Aug 2009
Location: Troy, NY, USA.
Posts: 592
Default Re: Problem 2.3 c

You will note from the definition of the hypothesis set: \cal H contains functions which are +1 for

a\le\sqrt{x_1^2+\cdots+x_d^2}\le b

You only get to vary a,b, and so the two spheres are restricted to be centered on the origin.

And yes, the m_{\cal H}(N) for this hypothesis set is very related to the growth function for positive intervals.

Quote:
Originally Posted by doris View Post
the last comment confused me a little bit.
For a given set of N points, we should change the center of the sphere to get as many dichotomies as we can, thus measuring the effective number of hypotheses (spheres) in this hypothesis set.

Does it make sense to move project the spheres from 3D to 1D and look at the problem as intervals of +1 for a<=x<=b and -a>=x>=b?
__________________
Have faith in probability
Reply With Quote
  #19  
Old 09-23-2012, 06:19 PM
mileschen mileschen is offline
Member
 
Join Date: Sep 2012
Posts: 11
Default Problem 2.15

In (a), it said that we should provide a monotonic classifier. Then, why there are +1 and -1 regions?

Also, as it said in (b) that generating the next point by increasing the first component and decreasing the second component. Then, how can we determine which point is larger? Because X1>=X2 if and only if the inequality is satisfied for every component. However, the next point is just with one component larger than that of the first one, while another component is less than that of the first one. So, it's a little confusing.
Reply With Quote
  #20  
Old 09-23-2012, 08:23 PM
magdon's Avatar
magdon magdon is offline
RPI
 
Join Date: Aug 2009
Location: Troy, NY, USA.
Posts: 592
Default Re: Problem 2.15

The function h is +1 in some region and is -1 in the complement - i.e. it takes on two values. Any function can be monotonic, even one that takes on just 2 values.

In (b), you are asked to compute m(N). To compute m(N) you need to count the maximum number of implementable dichotomys on some N points. The problem suggest a set of N points which might be helpful. The fact that no point is larger than another is crucial [hint: because if a point were larger than another, there is a dichotomy that you cannot implement].

Quote:
Originally Posted by mileschen View Post
In (a), it said that we should provide a monotonic classifier. Then, why there are +1 and -1 regions?

Also, as it said in (b) that generating the next point by increasing the first component and decreasing the second component. Then, how can we determine which point is larger? Because X1>=X2 if and only if the inequality is satisfied for every component. However, the next point is just with one component larger than that of the first one, while another component is less than that of the first one. So, it's a little confusing.
__________________
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 03:53 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.